Vulnerability database
Every flaw the U.S. government’s cybersecurity agency (CISA) has confirmed attackers are using, plus the new WordPress plugin and theme bugs published each day, sorted by what they mean for a small business. We refresh it twice a day. If you see something your website or office runs, tell us.
933 results · page 6 of 19
Aug 28, 2026A vulnerability was detected in iswalle getnote-mcp up to 1.5.0.CVE-2026-82111 · Other software · iswalle · reported by VulDBLow 2.1
A vulnerability was detected in iswalle getnote-mcp up to 1.5.0. The affected element is the function fs.readFileSync of the file src/index.ts of the component upload_image. Performing a manipulation of the argument image_path results in path traversal. The attack can be initiated remotely. The exploit is now public and may be used. Upgrading to version 1.5.1 is sufficient to fix this issue. The patch is named 7f9a215e03575c650d38c8f87fc6d8d363fed80d. Upgrading the affected component is advised.
- Product
- getnote-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 28, 2026In the Linux kernel, the following vulnerability has been resolved: net: dst_metadata: fix false-positive memcpy overflow in tun_dst_unclone kmalloc_flex() inCVE-2026-80615 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67High 8.2
In the Linux kernel, the following vulnerability has been resolved: net: dst_metadata: fix false-positive memcpy overflow in tun_dst_unclone kmalloc_flex() in metadata_dst_alloc() sets __counted_by for the structure to the options_len, which is then initialized to zero. Later, we're initializing the structure by copying the tunnel info together with the options, and this triggers a warning for a potential memcpy overflow, since the compiler estimates that the options can't fit into the structure, even though the memory for them is actually allocated. memcpy: detected buffer overflow: 104 byte write of buffer size 96 WARNING: CPU: X PID: Y at lib/string_helpers.c:1036 __fortify_report skb_tunnel_info_unclone+0x179/0x190 geneve_xmit+0x7fe/0xe00 The issue is triggered when built with clang and source fortification. Fix that by doing the copy in two stages: first - the main data with the options_len, then the options. This way the correct length should be known at the time of the copy. It would be better if the options_len never changed after allocation, but the allocation code is a little separate from the initialization and it would be awkward and potentially dangerous t
- Product
- Linux
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgit.kernel.orggit.kernel.org
Aug 27, 2026A vulnerability was determined in cyberchitta scrapling-fetch-mcp up to 0.2.2.CVE-2026-81848 · Other software · cyberchitta · reported by VulDBMedium 5.1
A vulnerability was determined in cyberchitta scrapling-fetch-mcp up to 0.2.2. The impacted element is the function s_fetch_page/s_fetch_pattern of the file src/scrapling_fetch_mcp/_fetcher.py. Executing a manipulation can lead to server-side request forgery. The attack can be launched remotely. Upgrading to version 0.2.3 is sufficient to resolve this issue. This patch is called 9f6f34e92c55c3d95566ad9c62aca7327d24533a. Upgrading the affected component is advised.
- Product
- scrapling-fetch-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026A vulnerability was found in MAA-AI MaaMCP up to 1.1.1.dev6+g2e4a41287.CVE-2026-81847 · Other software · MAA-AI · reported by VulDBLow 2
A vulnerability was found in MAA-AI MaaMCP up to 1.1.1.dev6+g2e4a41287. The affected element is the function save_pipeline/load_pipeline of the file pipeline_tools.py. Performing a manipulation results in path traversal. The attack can be initiated remotely. The exploit has been made public and could be used. The patch is named c93ef45cba75295eba26d9ff1ffb9202a91c6150. To fix this issue, it is recommended to deploy a patch.
- Product
- MaaMCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026A vulnerability has been found in arben-adm mcp-sequential-thinking up to 0.5.0.CVE-2026-81845 · Other software · arben-adm · reported by VulDBLow 2.1
A vulnerability has been found in arben-adm mcp-sequential-thinking up to 0.5.0. Impacted is the function import_session/export_session of the file mcp_sequential_thinking/server.py of the component Import Session/Export Session. Such manipulation of the argument file_path leads to path traversal. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. Upgrading to version 0.6.0 is recommended to address this issue. The name of the patch is 2fad3ee8ab1d0868b6c1afb5895bc336a10e5267. Upgrading the affected component is recommended.
- Product
- mcp-sequential-thinking
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026startServer.ts in the mcp-http-server package of UI-TARS-desktop defaulted its listen address to '::' when no host was given, so startSseAndStreamableHttpMcpSerCVE-2026-81735 · Other software · bytedance · reported by VulnCheckCritical 10
startServer.ts in the mcp-http-server package of UI-TARS-desktop defaulted its listen address to '::' when no host was given, so startSseAndStreamableHttpMcpServer bound the Streamable HTTP and SSE MCP transports to every interface, and its authentication middleware was optional: middlewares are applied only when a caller supplies them. The @agent-infra/mcp-server-commands and @agent-infra/mcp-server-filesystem entry points call startSseAndStreamableHttpMcpServer with a host and port alone and pass no middleware, so neither server required a credential. The commands server exposes a run_command tool that hands its caller-supplied command string to promisify(child_process.exec), so any unauthenticated client able to reach the port could run arbitrary commands as the user running the server, and the filesystem server exposed its file read and write tools on the same terms. The listen default became 127.0.0.1 in commit c2ad42e3eb9b27830db41a3e6f51ca7179d9b168; the package version stayed at 1.2.4 across that change, so the boundary is the commit rather than a release.
- Product
- UI-TARS-desktop
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026The Dash MCP server bound its listener to the loopback address but never checked the host a request named.CVE-2026-81102 · Other software · dropbox · reported by VulnCheckLow 2.3
The Dash MCP server bound its listener to the loopback address but never checked the host a request named. src/mcp_server_dash.py constructed the server for its network mode with the interface restricted to loopback and no transport-security settings, so a name that had been pointed at the loopback address still reached the listener while carrying the attacker's host name. A page in a visitor's browser could therefore drive the local server and invoke its company-search and file-detail tools under the Dropbox credential the server holds. Only the network mode was reachable this way; the standard input mode was not. The fix supplies transport-security settings that enable host checking and allow only the loopback name and port, rejecting other hosts before a tool runs. The repository publishes no versions, so the affected boundary is the commit preceding the fix.
- Product
- mcp-server-dash
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026The configure command accepted any endpoint URL and stored it beside the user's access token.CVE-2026-81101 · Other software · Airtable · reported by VulnCheckMedium 6.9
The configure command accepted any endpoint URL and stored it beside the user's access token. ConfigureCommand.execute in src/cli.ts persisted the value given to its endpoint option into the user profile without passing it through createSafeUrl in src/config.ts, the helper that already restricted the environment-variable form of the same setting to the vendor's own hosts over HTTPS. Because the connect path in src/mcp.ts attaches the stored token as a bearer credential on every request to the configured endpoint, a user who was persuaded to run configure with an endpoint of the attacker's choosing sent their personal access token to that destination on each subsequent invocation. Version 0.2.5 applies the same helper to the option.
- Product
- airtable-mcp-cli
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026tiger-gh-mcp-server started its MCP HTTP transport without enabling the host allow-list the underlying SDK provides.CVE-2026-81100 · Other software · timescale · reported by VulnCheckHigh 7.6
tiger-gh-mcp-server started its MCP HTTP transport without enabling the host allow-list the underlying SDK provides. src/httpServer.ts called the shared httpServerFactory helper and never set the DNS-rebinding-protection option, so the transport accepted a request whatever host it named, making the locally reachable GitHub MCP endpoint drivable from a page in a visitor's browser that pointed a name it controlled at the bound address. The fix passes the option explicitly alongside a dependency update; the update alone would not have closed it. The repository has published no release that brackets the fix, so the affected boundary is the commit preceding it.
- Product
- tiger-gh-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026tiger-slack started its MCP HTTP transport without enabling the host allow-list the underlying SDK provides.CVE-2026-81099 · Other software · timescale · reported by VulnCheckHigh 7.6
tiger-slack started its MCP HTTP transport without enabling the host allow-list the underlying SDK provides. mcp/src/httpServer.ts called the shared httpServerFactory helper and never set the DNS-rebinding-protection option, so the transport accepted a request whatever host it named, and a page in a browser could point a name it controlled at the address the server was bound to and drive the locally reachable Slack MCP server through the visitor's browser. The fix passes the option explicitly alongside a dependency update; the update alone would not have closed it. The repository publishes no release that brackets the fix, so the affected boundary is the commit preceding it.
- Product
- tiger-slack
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026The Telnyx MCP server exposed its HTTP transport on every interface and did not require a caller credential.CVE-2026-81098 · Other software · team-telnyx · reported by VulnCheckCritical 9.3
The Telnyx MCP server exposed its HTTP transport on every interface and did not require a caller credential. packages/mcp-server/src/http.ts served MCP on the root path with a listener bound to all interfaces and parsed the caller's authentication headers in a mode that did not fail when they were absent, so a request without any credential completed initialisation and dispatched tools. Dispatch forwarded the server's own stored credentials, the Telnyx API key and client secret together with the code-execution key, to the upstream endpoint, so an unauthenticated caller able to reach the port acted with them. The current code defaults the host to loopback, requires a server API key, and enforces it in middleware.
- Product
- telnyx-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026The execute_ruby tool is documented as a read-only Ruby sandbox and is enforced by a pattern denylist together with replacements for the process-spawning methodCVE-2026-81097 · Other software · maquina-app · reported by VulnCheckHigh 8.6
The execute_ruby tool is documented as a read-only Ruby sandbox and is enforced by a pattern denylist together with replacements for the process-spawning methods on Kernel. The pseudo-terminal library's spawn entry points are neither in the denylist nor replaced, so a normal tool call could reach them and start a shell, executing commands as the account running the server and outside the guarded methods. The denylist was introduced with the tool in 1.4.0 and never covered those entry points through 1.6.0. Version 1.6.1 restricts the requires the sandbox permits to a data-only list and blocks dynamic dispatch to execution entry points; 2.0.0 removes the tool.
- Product
- rails-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026pg-aiguide started its MCP HTTP transport without enabling the host allow-list the underlying SDK provides.CVE-2026-81095 · Other software · timescale · reported by VulnCheckHigh 7.6
pg-aiguide started its MCP HTTP transport without enabling the host allow-list the underlying SDK provides. src/httpServer.ts called the shared httpServerFactory helper and never set the DNS-rebinding-protection option, so the transport accepted a request whatever host it named. A page in a browser could therefore point a name it controlled at the address the server was bound to and drive the locally reachable MCP server through the visitor's browser. The protection was already available in the packaged transport and simply not turned on, so updating the dependency alone would not have closed it. Version 0.5.1 passes the option explicitly.
- Product
- pg-aiguide
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026The mcp-router CLI served its MCP aggregator on every interface and enforced authentication only when the operator asked for it.CVE-2026-81094 · Other software · mcp-router · reported by VulnCheckCritical 9.3
The mcp-router CLI served its MCP aggregator on every interface and enforced authentication only when the operator asked for it. The serve command in apps/cli/src/commands/serve.ts defaulted its host to the all-interfaces address on a fixed port, and required a token only when the corresponding flag was supplied, so a default invocation exposed the aggregator, and every MCP server it fronted, to anyone able to reach the port. Release 0.6.3 defaults the host to the loopback address and refuses to start without a token whenever the host it is given is not a loopback address; no earlier release carries either check.
- Product
- mcp-router
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026The get-html-skeleton tool fetched a URL the caller supplied after checking only its syntax.CVE-2026-81093 · Other software · apify · reported by VulnCheckHigh 8.7
The get-html-skeleton tool fetched a URL the caller supplied after checking only its syntax. The handler in src/tools/common/get_html_skeleton.ts validated the url argument with isValidHttpUrl from src/utils/generic.ts, which confirmed the string began with an http or https scheme and parsed as a URL and inspected neither the host name nor the address it resolves to. Loopback, link-local and private ranges therefore passed, including the address cloud providers use to serve instance metadata. The unchecked URL was handed to the web-browser actor and the fetched document was returned in the tool response, so any caller of the MCP server could make it request an endpoint reachable only from the host and read the result, including instance credentials. Version 0.9.12 removes the tool.
- Product
- actors-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026mcp-go accepted requests on its HTTP transports without checking the Host header.CVE-2026-81092 · Other software · mark3labs · reported by VulnCheckHigh 7.6
mcp-go accepted requests on its HTTP transports without checking the Host header. StreamableHTTPServer.ServeHTTP in server/streamable_http.go and SSEServer.ServeHTTP in server/sse.go served any request arriving over a loopback connection regardless of the host it named, and the SSE transport's cross-origin default allowed any origin. A page in a browser could therefore point a name it controlled at the loopback address and reach a server listening there, invoking tools and reading resources that the server exposed on the assumption that only local software could connect. No release before 0.56.0 validated the header on either transport; 0.56.0 adds server/http_localhost.go, which rejects a loopback-bound request carrying a host that is not a loopback name, and wires it into both transports.
- Product
- mcp-go
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026The proxy middleware in mcp-use's inspector forwards requests to a destination the caller names.CVE-2026-81091 · Other software · mcp-use · reported by VulnCheckHigh 8.7
The proxy middleware in mcp-use's inspector forwards requests to a destination the caller names. mountMcpProxy in libraries/typescript/packages/inspector/src/server/proxy/mcp-proxy.ts read the target from the X-Target-URL header or the __mcp_target parameter and proxied to it without inspecting the host, so loopback, link-local and private addresses were all accepted, as were names that resolve to them, and the validation was not reapplied to a redirect the destination returned. A caller could therefore make the server issue requests to addresses reachable only from the host it runs on and read the responses. The current code calls isSafeProxyTarget, which checks the resolved address against private, loopback and link-local ranges before proxying and bounds the number of redirects followed.
- Product
- mcp-use
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 27, 2026A flaw has been found in boxpositron with-context-mcp up to 3.0.7.CVE-2026-81491 · Other software · boxpositron · reported by VulDBMedium 5.5
A flaw has been found in boxpositron with-context-mcp up to 3.0.7. This affects the function ingest_notes/teleport_notes/sync_notes/project_folder of the file src/index.ts. Executing a manipulation can lead to path traversal. It is possible to launch the attack remotely. The exploit has been published and may be used. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- with-context-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 26, 2026A vulnerability was detected in bsmi021 mcp-file-context-server 1.0.0.CVE-2026-81486 · Other software · bsmi021 · reported by VulDBMedium 5.5
A vulnerability was detected in bsmi021 mcp-file-context-server 1.0.0. Affected by this issue is the function read_context of the file src/index.ts of the component Path Resolution. Performing a manipulation of the argument path results in path traversal. It is possible to initiate the attack remotely. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- mcp-file-context-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 26, 2026A security vulnerability has been detected in danielpopamd linkedin-ads-mcp 1.0.0.CVE-2026-81485 · Other software · danielpopamd · reported by VulDBMedium 5.5
A security vulnerability has been detected in danielpopamd linkedin-ads-mcp 1.0.0. Affected by this vulnerability is the function fs.readFileSync of the file src/tools/campaign-management.ts of the component Media Upload. Such manipulation of the argument filePath leads to path traversal. The attack may be performed from remote. The exploit has been disclosed publicly and may be used. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- linkedin-ads-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 26, 2026A security flaw has been discovered in ddfourtwo sentry-selfhosted-mcp 0.4.0.CVE-2026-81421 · Other software · ddfourtwo · reported by VulDBMedium 5.5
A security flaw has been discovered in ddfourtwo sentry-selfhosted-mcp 0.4.0. The affected element is an unknown function of the component raw_sentry_api. The manipulation of the argument endpoint results in server-side request forgery. It is possible to launch the attack remotely. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- sentry-selfhosted-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 26, 2026mcp-fetch checks a fetch target against its SSRF guard without removing the brackets that surround an IPv6 literal.CVE-2026-80347 · Other software · kazuph · reported by VulnCheckHigh 8.7
mcp-fetch checks a fetch target against its SSRF guard without removing the brackets that surround an IPv6 literal. isSafeUrl reads the hostname from the parsed URL, which for a literal such as http://[::1]/ yields the bracketed string, and then tests it with net.isIP. That call returns zero for a bracketed value, so the branch holding the private-address checks is skipped entirely. The guard falls back to resolving the hostname, the bracketed string is not a resolvable name, no addresses are returned, and the target is reported safe. The HTTP client then strips the brackets and connects. Because the address may be given in IPv4-mapped form, the same path reaches any IPv4 target the loopback and private checks were meant to exclude, including link-local metadata endpoints. isPrivateIPv6 also has no case for the ::ffff: prefix, so the mapped form would still pass even if the brackets were removed. The fetch target is supplied as a tool argument, so an attacker who can influence what the model requests can read internal responses back into the model context.
- Product
- mcp-fetch
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026The MCP PHP SDK (Composer package mcp/sdk) is the official Model Context Protocol SDK for PHP.CVE-2026-53965 · Other software · modelcontextprotocol · reported by GitHubMedium 6.9
The MCP PHP SDK (Composer package mcp/sdk) is the official Model Context Protocol SDK for PHP. In versions 0.5.0 through 0.7.0, the HTTP client transport reads a Server-Sent Events response stream incrementally and appends each chunk to an in-memory buffer with no upper bound. The buffer is only flushed when an SSE event delimiter, a double newline, is found, so a remote MCP server that streams response bytes without ever sending the delimiter causes the buffer to grow without limit. A malicious, compromised, or man-in-the-middle-controlled server that the client connects to over the HTTP transport can exploit this to exhaust the client process's memory, triggering a fatal allocation error or OS out-of-memory kill and denying service to the MCP client. The issue affects any client using HttpTransport against an untrusted server endpoint and does not require authentication or user interaction beyond initiating the connection. This issue is fixed in version 0.7.1.
- Product
- php-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026Coroot's unauthenticated MCP OAuth dynamic client registration endpoint accepts any syntactically valid redirect URI without validation, allowing attackers to rCVE-2026-79786 · Other software · coroot · reported by VulnCheckHigh 7
Coroot's unauthenticated MCP OAuth dynamic client registration endpoint accepts any syntactically valid redirect URI without validation, allowing attackers to register clients pointing to attacker-controlled hosts. Attackers can send authorization URLs to signed-in users, capture their authorization codes upon consent approval, and exchange them for access tokens to hijack MCP sessions.
- Product
- coroot
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026genieacs-mcp is an MCP server for GenieACS written in Go.CVE-2026-55637 · Other software · GeiserX · reported by GitHubHigh 8.8
genieacs-mcp is an MCP server for GenieACS written in Go. Prior to 0.3.2, the Streamable HTTP transport in cmd/server/main.go creates an unauthenticated /mcp listener on the default MCP_LISTEN_ADDR value 127.0.0.1:8080 when MCP_AUTH_TOKEN is unset and the httpSrv.Start(addr) branch does not validate the Host or Origin headers. A malicious website can use DNS rebinding to send browser requests with attacker-controlled Host and Origin values to the loopback listener, initialize an MCP session, list tools, and invoke operations against the GenieACS NBI configured by ACS_URL. Successful exploitation can expose or modify CPE management state, including device reboots, firmware tasks, TR-069 parameter changes, presets, provisions, tags, connection requests, and task operations. The npm wrapper is not affected because it forces TRANSPORT=stdio and does not expose an HTTP listener. This issue is fixed in version 0.3.2.
- Product
- genieacs-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents.CVE-2026-55557 · Other software · That1Drifter · reported by GitHubHigh 8.6
browse-mcp is a Playwright-based headless-browser MCP server for MCP-capable agents. Prior to 0.8.2, browser_download writes a fetched response body to join(save_dir, filename) without validating the caller-controlled save_dir, while browser_save_state and browser_load_state honor a caller-controlled path unchanged. A malicious MCP client, or an autonomous agent steered by indirect prompt injection on a visited page, can choose an arbitrary save_dir or state path and a URL whose response body becomes attacker-controlled file contents, allowing writes to any path the process can reach, including ~/.bashrc, autostart entries, or cron files, and potentially leading to host code execution. The force_fetch fallback also uses a raw fetch() that bypasses the BROWSE_MCP_ALLOWED_ORIGINS origin fence. This issue is fixed in version 0.8.2.
- Product
- browse-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026Nextcloud MCP Server is a production-ready MCP server that connects AI assistants to a Nextcloud instance.CVE-2026-55640 · Other software · cbcoutinho · reported by GitHubCritical 9.1
Nextcloud MCP Server is a production-ready MCP server that connects AI assistants to a Nextcloud instance. Prior to 0.117.2, the POST /webhooks/nextcloud endpoint in nextcloud_mcp_server/vector/webhook_receiver.py has no authentication by default because WEBHOOK_SECRET defaults to None and startup validation does not require it. When WEBHOOK_SECRET is unset, handle_nextcloud_webhook() accepts unauthenticated requests. The payload["user"]["uid"] field parsed in nextcloud_mcp_server/vector/webhook_parser.py is attacker-controlled and is used without an authenticated-session cross-check for Qdrant operations, allowing a network attacker to delete or trigger re-indexing of vector embeddings for any user and to destroy the semantic search index by sending forged deletion events. This issue is fixed in version 0.117.2.
- Product
- nextcloud-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026mcp-shell is an MCP server for running shell commands securely, auditably, and on demand.CVE-2026-55582 · Other software · sonirico · reported by GitHubHigh 8.4
mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, the default security.yaml allows /usr/bin/git, while security.go omits ! from containsShellMetacharacters and containsDangerousShellConstructs and applies no per-executable argument policy. A caller of the shell_exec MCP tool can provide the command argument /usr/bin/git -c alias.pwn=!<arbitrary-command>, causing Git to create a shell alias and execute arbitrary OS commands as the mcp-shell process user. The default Docker image runs as mcpuser with Git installed and secure mode enabled, so the bypass is exploitable in the default deployment without additional authentication beyond MCP connectivity. This issue is fixed in version 0.6.0.
- Product
- mcp-shell
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026mcp-shell is an MCP server for running shell commands securely, auditably, and on demand.CVE-2026-55581 · Other software · sonirico · reported by GitHubHigh 8.4
mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, the default Docker security.yaml includes /bin/bash in allowed_executables, while security.go validates only the first token and checkBlockedPatternsAndCommands does not reject the shell command-mode flag -c. A caller of the shell_exec MCP tool can provide the command argument `/bin/bash -c <arbitrary-command>`, which passes validation and reaches executor.go, where parseCommand and exec.CommandContext execute the arbitrary command as mcpuser outside the intended allowlist. This issue is fixed in version 0.6.0.
- Product
- mcp-shell
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026mcp-shell is an MCP server for running shell commands securely, auditably, and on demand.CVE-2026-55580 · Other software · sonirico · reported by GitHubHigh 8.6
mcp-shell is an MCP server for running shell commands securely, auditably, and on demand. Prior to 0.6.0, config.go initializes Security.Enabled to false, and when MCP_SHELL_SEC_CONFIG_FILE is unset, main.go starts the documented bare-binary deployment without a security policy. SecurityValidator.validateCommand in security.go then short-circuits and allows every command supplied to the shell_exec MCP tool, so an LLM connected over stdio can execute unrestricted OS commands as the mcp-shell process user. The README from-source installation and MCP client configuration omit MCP_SHELL_SEC_CONFIG_FILE, making the insecure state the documented default. This issue is fixed in version 0.6.0.
- Product
- mcp-shell
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026QWED-MCP is a deterministic verification gateway for MCP.CVE-2026-55546 · Other software · QWED-AI · reported by GitHubCritical 9.8
QWED-MCP is a deterministic verification gateway for MCP. Prior to 0.2.1, verify_math_expression() in src/qwed_mcp/engines/math_engine.py passes attacker-controlled expression and claimed_result strings directly to SymPy's parse_expr() after only normalizing caret syntax to Python exponent syntax, without restricting global_dict, removing Python built-ins, or validating the expression AST. Because parse_expr() calls Python's eval() with built-ins available, an attacker who can cause a downstream caller to pass untrusted input to this public library function can use Python import functionality to execute arbitrary operating-system commands as the qwed-mcp process user, read or modify accessible data, exfiltrate process secrets, or reach internal services. The default MCP tool registry does not expose verify_math_expression(), so exploitation requires a downstream integration that invokes the library API with attacker-controlled input. This issue is fixed in version 0.2.1.
- Product
- qwed-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 25, 2026A weakness has been identified in dekdee adobe-xd-mcp 1.0.0.CVE-2026-79622 · Other software · dekdee · reported by VulDBMedium 5.5
A weakness has been identified in dekdee adobe-xd-mcp 1.0.0. Impacted is an unknown function of the file src/parsers/xd-parser.ts of the component file-access-from-request Endpoint. Executing a manipulation of the argument outputFile/outputDir can lead to path traversal. It is possible to launch the attack remotely. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- adobe-xd-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 24, 2026BetterLinks – Link Shortener, Link Cloaking, Redirects, Affiliate Link Manager & MCP: Authorization bypassCVE-2026-19801 · WordPress plugins & themes · reported by WordfenceMedium 4.3
The BetterLinks – Link Shortener, Link Cloaking, Redirects, Affiliate Link Manager & MCP plugin for WordPress is vulnerable to authorization bypass in all versions up to, and including, 3.1.0. This is due to the plugin not properly verifying that a user is authorized to perform an action. This makes it possible for authenticated attackers, with subscriber-level access and above, to create arbitrary BetterLinks short URLs with attacker-controlled slugs and redirect destinations, enabling phishing and SEO abuse. Exploitation requires the Fluent Boards companion plugin to be installed and active (so that the FLUENT_BOARDS constant is defined), and is further facilitated by the betterlinks_admin_nonce nonce being emitted on every frontend page via wp_localize_script, making it accessible to any authenticated user.
- Product
- BetterLinks – Link Shortener, Link Cloaking, Redirects, Affiliate Link Manager & MCP
- Affected
- up to 3.1.0
- What to do
- Affects up to 3.1.0. Update BetterLinks – Link Shortener, Link Cloaking, Redirects, Affiliate Link Manager & MCP to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Full record and what to do →NVD recordplugins.trac.wordpress.orgplugins.trac.wordpress.org
Aug 24, 2026A vulnerability was detected in sworddut mcp-ffmpeg-helper 0.1.0/0.1.1/0.2.1.CVE-2026-78430 · Other software · sworddut · reported by VulDBLow 1.9
A vulnerability was detected in sworddut mcp-ffmpeg-helper 0.1.0/0.1.1/0.2.1. This affects the function handleToolCall of the file src/tools/handlers.ts of the component Tool Handler. The manipulation of the argument format results in os command injection. Attacking locally is a requirement. The exploit is now public and may be used. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- mcp-ffmpeg-helper
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 22, 2026SiYuan versions before v3.8.0 contain an incomplete path blocklist in the MCP file tool that fails to restrict access to sensitive workspace files protected by CVE-2026-60083 · Other software · siyuan-note · reported by VulnCheckMedium 6.9
SiYuan versions before v3.8.0 contain an incomplete path blocklist in the MCP file tool that fails to restrict access to sensitive workspace files protected by the HTTP API. Authenticated administrators can read plaintext publish-mode passwords from data/.siyuan/publishAccess.json and access other sensitive files like data/templates and data/snippets/conf.json.
- Product
- siyuan
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Aug 22, 2026SiYuan before v3.8.0 interpolates secret placeholders into the destination URL parameter of the http_request MCP tool, allowing attackers to exfiltrate stored sCVE-2026-59809 · Other software · siyuan-note · reported by VulnCheckMedium 6.9
SiYuan before v3.8.0 interpolates secret placeholders into the destination URL parameter of the http_request MCP tool, allowing attackers to exfiltrate stored secrets. An MCP client can craft a request with an attacker-controlled URL containing secret placeholders to send plaintext secret values to any public host without confirmation.
- Product
- siyuan
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Aug 21, 2026CKAN MCP Server is a tool for querying CKAN open data portals.CVE-2026-53509 · Other software · ondata · reported by GitHubMedium 5.7
CKAN MCP Server is a tool for querying CKAN open data portals. A known vulnerability CVE-2026-33060 indicated tools including ckan_package_search and sparql_query that accept a base_url parameter had the risk of making HTTP requests to arbitrary endpoints without restriction. A fix was applied to filter out ip addresses. However, a method to bypass exists prior to version 0.4.106. CKAN MCP Server validates caller-supplied CKAN server URLs by inspecting only the parsed hostname string before issuing outbound HTTP requests. In `src/utils/http.ts`, hostname aliases such as `ip6-localhost` are not equal to `localhost`, are not dotted IPv4 literals, and are not bracketed IPv6 literals, so they pass the SSRF filter but can resolve to loopback when the server performs the request. A remote MCP caller that can invoke CKAN tools with a `server_url` can therefore make the server connect to local or private addresses and, for CKAN-shaped responses, receive response-derived data. The updated fix in version 0.4.106 replaced the single `hostname === 'localhost'` check with a blocked-hostname `Set` covering `ip6-localhost` and `ip6-loopback`.
- Product
- ckan-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 21, 2026The MCP Streamable HTTP server transport (WebFlux and WebMvc variants) does not place any limit on the number of sessions it retains, and by default does not reCVE-2026-59279 · Other software · Spring · reported by security@vmware.comHigh 7.5
The MCP Streamable HTTP server transport (WebFlux and WebMvc variants) does not place any limit on the number of sessions it retains, and by default does not require clients to be authenticated. As a result, a remote attacker can cause the server to accumulate an unbounded number of sessions over time, gradually exhausting available memory and ultimately causing a Denial of Service that affects all legitimate clients. Affected versions: Spring AI: 2.0.0
- Product
- Spring AI
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 20, 2026Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntaxCVE-2026-18482 · Other software · Klarso GmbH · reported by cret@cert.orgCritical 9.8
Neo.mjs contains a command injection vulnerability within the FileSystemService.mjs component of the ai/mcp/server/file-system MCP server, where the checkSyntax() and runPlaywrightTest() functions unsafely interpolate caller-controlled absolutePath values into shell commands, enabling arbitrary OS command execution when an AI agent is induced to invoke these tools. Commit 88c77fc fixes these vulnerabilities.
- Product
- neo-mjs
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 20, 2026n8n versions before 2.34.1 contain a credential validation bypass in the MCP create_workflow_from_code tool when authentication type is set to an expression.CVE-2026-77073 · Other software · n8n-io · reported by VulnCheckMedium 5.3
n8n versions before 2.34.1 contain a credential validation bypass in the MCP create_workflow_from_code tool when authentication type is set to an expression. Attackers with a valid MCP Bearer API key and knowledge of a target credential ID can persist unauthorized cross-project credential references on workflows in different projects.
- Product
- n8n
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Aug 20, 2026n8n before 2.33.4 and 2.34.x before 2.34.1 contain a remote code execution vulnerability in the @n8n/workflow-sdk node-schema loader used for MCP node-schema loCVE-2026-77068 · Other software · n8n-io · reported by VulnCheckHigh 8.7
n8n before 2.33.4 and 2.34.x before 2.34.1 contain a remote code execution vulnerability in the @n8n/workflow-sdk node-schema loader used for MCP node-schema loading. The loader derives a node's schema module path directly from the attacker-supplied node type string without validating path-traversal sequences. An authenticated user with global:member privileges can reference malicious files via path traversal, causing code execution in the n8n main process.
- Product
- n8n
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Aug 19, 2026In Splunk MCP Server app versions below 1.2.1, a user who holds the "admin" Splunk role could execute arbitrary commands on the underlying operating system.CVE-2026-76404 · Other software · Splunk · reported by psirt@cisco.comCritical 9.1
In Splunk MCP Server app versions below 1.2.1, a user who holds the "admin" Splunk role could execute arbitrary commands on the underlying operating system. The vulnerability is possible because of missing input validation in the app's credential management component, which deserializes stored data without checking whether the content is of the expected type.
- Product
- Splunk MCP Server app
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 18, 2026The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store.CVE-2026-50143 · Other software · apify · reported by GitHubHigh 8.1
The Apify MCP server enables AI agents to extract data from websites using ready-made scrapers, crawlers, and automation tools available on the Apify Store. Prior to 0.10.11, getActorMCPServerURL in src/mcp/actors.ts concatenates the trusted Actor standby URL with the attacker-controlled webServerMcpPath from an Actor definition without verifying the resulting origin, allowing a malicious Actor publisher to use a userinfo-style authority value to redirect connectMCPClient to a third-party host. The call-actor, fetch-actor-details, and actor-mcp tool-loading paths pass this URL to transports in src/mcp/client.ts that attach the victim Authorization bearer token, exposing the Apify API token and enabling access to Actors, stored data, and billable compute. A victim must invoke or inspect the attacker-controlled Actor. This issue is fixed in version 0.10.11.
- Product
- apify-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 18, 2026ArcadeDB versions 26.4.2 through 26.7.3 contain an authorization bypass vulnerability in the set_server_setting MCP server-level tool.CVE-2026-75845 · Other software · ArcadeData · reported by VulnCheckMedium 5.3
ArcadeDB versions 26.4.2 through 26.7.3 contain an authorization bypass vulnerability in the set_server_setting MCP server-level tool. SetServerSettingTool.execute() gates only on the global allowAdmin flag and never checks the caller's role, so in an MCP deployment with allowAdmin=true and a non-root allowedUsers set, any authenticated read-only user can invoke set_server_setting to modify server GlobalConfiguration, enabling configuration tampering or denial of service. The issue is fixed in 26.8.1.
- Product
- arcadedb
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Aug 18, 2026SSRF via set_skywalking_url Tool and GraphQL expression injection vulnerability in Apache SkyWalking MCP.CVE-2026-34884 · Websites & servers · Apache Software Foundation · reported by security@apache.orgCritical 9.8
SSRF via set_skywalking_url Tool and GraphQL expression injection vulnerability in Apache SkyWalking MCP. This issue affects Apache SkyWalking MCP: 0.1.0. Users are recommended to upgrade to version 0.2.0, which fixes this issue.
- Product
- Apache SkyWalking MCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordlists.apache.orgopenwall.com
Aug 17, 2026A flaw has been found in kylecui NetForensicMCP 2.1.0.CVE-2026-75011 · Other software · kylecui · reported by VulDBLow 2.1
A flaw has been found in kylecui NetForensicMCP 2.1.0. Impacted is the function execAsync of the file index.js. Executing a manipulation of the argument interface/protocol can lead to command injection. The attack may be launched remotely. The exploit has been published and may be used. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- NetForensicMCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 17, 2026In JetBrains PyCharm before 2026.2.1 code execution was possible via unauthenticated Jupyter MCP toolsCVE-2026-75060 · Other software · JetBrains · reported by cve@jetbrains.comHigh 8.4
In JetBrains PyCharm before 2026.2.1 code execution was possible via unauthenticated Jupyter MCP tools
- Product
- PyCharm
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 17, 2026A vulnerability has been found in jae-jae fetcher-mcp up to 0.3.9.CVE-2026-74858 · Other software · jae-jae · reported by VulDBMedium 5.3
A vulnerability has been found in jae-jae fetcher-mcp up to 0.3.9. Impacted is the function fetch_url/fetch_urls of the file /latest/meta-data/iam/security-credentials/ of the component URL Validation. Such manipulation leads to server-side request forgery. It is possible to launch the attack remotely. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- fetcher-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 17, 2026A vulnerability was found in Kira-Pgr PromptShopMCP up to 5bc0cd17358e19a5415d11a531088170d7b81452.CVE-2026-74842 · Other software · Kira-Pgr · reported by VulDBLow 2.1
A vulnerability was found in Kira-Pgr PromptShopMCP up to 5bc0cd17358e19a5415d11a531088170d7b81452. Affected is the function download_image of the file server.py of the component Image-Toolkit-MCP-Server. Performing a manipulation of the argument image_url results in server-side request forgery. The attack may be initiated remotely. The exploit has been made public and could be used. This product uses a rolling release model to deliver continuous updates. As a result, specific version information for affected or updated releases is not available. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- PromptShopMCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 17, 2026SiYuan kernel before v3.7.4 contains a path traversal vulnerability in the database_clean MCP tool.CVE-2026-74798 · Other software · siyuan-note · reported by VulnCheckCritical 9.3
SiYuan kernel before v3.7.4 contains a path traversal vulnerability in the database_clean MCP tool. The tool performs only an empty-string check on the id parameter before passing it to RemoveUnusedAttributeView (kernel/model/attribute_view.go), which builds a filesystem path via filepath.Join without validating that id matches SiYuan's node-ID format. An authenticated MCP client can supply path traversal sequences in id to cause the kernel to copy an arbitrary file readable by the process into SiYuan's history directory (arbitrary file read) and then delete the original file (arbitrary file deletion). The corresponding HTTP API handler was hardened in GHSA-7hm9-v7vf-7g4w, but this MCP caller was not.
- Product
- siyuan
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comvulncheck.com
Where this comes from: the exploited list is CISA’s Known Exploited Vulnerabilities catalog. Everything else is the whole National Vulnerability Database, where each record is published by the team that found the bug (Wordfence, Patchstack, WPScan, the vendors themselves and others); we show who. Exploit odds are FIRST’s EPSS, updated daily. Titles and categories are ours, so check the linked record before acting on a detail. For a write-up of the big ones, see our advisories. Every vendor, and every WordPress plugin and theme with a recorded flaw, also has its own page. All of it is free to reuse as JSON, CSV or RSS.
Weekly security brief
The flaws that hit local websites, every Friday.
One short email: what got exploited this week, which WordPress plugins broke, and what to check. Unsubscribe in one click.
Tell us what you're building.
A website, your marketing, a security check, an app, or the thing you've been running out of a spreadsheet for three years. A few lines is plenty.
Not ready to talk yet? Run the free website check and see what Google sees.