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 2 of 19
Oct 14, 2026The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP).CVE-2026-59951 · Other software · modelcontextprotocol · reported by GitHubMedium 6.9
The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP). From 1.8.0 until 1.30.0 and 2.2.0, stateful Streamable HTTP servers, including FastMCP, MCPServer, Server.streamable_http_app(), and StreamableHTTPSessionManager, retain session entries without an idle expiration or aggregate session-count limit. DELETE, refused opening requests, and completed sessions do not reliably discard their entries, and each entry can retain parsed initialize parameters. A client that can reach the endpoint can therefore create ordinary short requests that grow server memory without bound until restart. Stateless HTTP, stdio, and SSE transports are not affected. This issue is fixed in versions 1.30.0 and 2.2.0.
- Product
- python-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 13, 2026MCP Context Forge provides an MCP Admin UI for managing gateway resources.CVE-2026-53711 · Other software · IBM · reported by GitHubMedium 5.1
MCP Context Forge provides an MCP Admin UI for managing gateway resources. From 0.2.0 until 0.3.1, the Global Prompts feature stores a prompt template without sufficient output encoding before the MCP Admin UI renders it. An authenticated attacker can save markup containing script-capable event handlers, and the code executes when another user views the saved prompt. The stored cross-site scripting can alter the interface, present phishing content, observe keystrokes available to the page, and act with the viewer's browser session. This issue is fixed in version 0.3.1.
- Product
- mcp-context-forge
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 13, 2026MCP Context Forge is an MCP gateway and administrative platform.CVE-2026-53709 · Other software · IBM · reported by GitHubCritical 9.8
MCP Context Forge is an MCP gateway and administrative platform. Prior to 1.0.2, mcpgateway/config.py and .env.example ship a known JWT_SECRET_KEY, while verify_jwt_token() accepts HS256 tokens signed with that key and get_current_user() creates a platform administrator when the token subject matches PLATFORM_ADMIN_EMAIL and REQUIRE_USER_IN_DB is false. A remote unauthenticated attacker can therefore mint accepted administrator tokens without a database account. While the vulnerable signing key remains configured and the platform-admin bootstrap remains enabled, forged access survives password rotation, account deletion, and session revocation, allowing administrative disclosure, modification, and service disruption. This issue is fixed in version 1.0.2.
- Product
- mcp-context-forge
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 12, 2026Network-AI (npm network-ai) before 5.15.2 contains an origin validation error in McpSseServer._handleRequest in lib/mcp-transport-sse.ts that reflects localhostCVE-2026-109332 · Other software · Jovancoding · reported by VulnCheckLow 2.3
Network-AI (npm network-ai) before 5.15.2 contains an origin validation error in McpSseServer._handleRequest in lib/mcp-transport-sse.ts that reflects localhost Origins into Access-Control-Allow-Origin regardless of bind interface. When the server binds a non-loopback address, an attacker page with a localhost Origin visited by a victim can read unauthenticated endpoints like /health cross-origin.
- Product
- Network-AI
- 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
Oct 12, 2026mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharactCVE-2026-108953 · Other software · cfdude · reported by VulnCheckHigh 8.5
mac-shell-mcp before 2.0.0 contains an OS command injection vulnerability that allows MCP clients to bypass the command whitelist by injecting shell metacharacters into execute_command arguments. Attackers or malicious prompts can call a safe command such as pwd with arguments like ';' to run forbidden commands as the server user without approval.
- Product
- mac-shell-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026A vulnerability was found in houtini-ai voice-analyser-mcp up to 2.1.1.CVE-2026-108787 · Other software · houtini-ai · reported by VulDBLow 2.1
A vulnerability was found in houtini-ai voice-analyser-mcp up to 2.1.1. The affected element is the function fetch of the file src/utils/crawler.ts of the component collect_corpus. Performing a manipulation of the argument sitemap_url results in server-side request forgery. Remote exploitation of the attack is possible. The exploit has been made public and could be used. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- voice-analyser-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026A vulnerability has been found in houtini-ai seo-crawler-mcp up to 2.1.5.CVE-2026-108786 · Other software · houtini-ai · reported by VulDBLow 2.1
A vulnerability has been found in houtini-ai seo-crawler-mcp up to 2.1.5. Impacted is the function run_seo_audit of the file src/core/CrawlOrchestrator.ts of the component Crawler. Such manipulation leads to server-side request forgery. The attack may be launched remotely. The exploit has been disclosed to the public and may be used. The vendor was contacted early about this disclosure but did not respond in any way.
- Product
- seo-crawler-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026Odoo MCP 1.0.0 through 1.3.2 contains an information disclosure vulnerability that allows MCP clients to bypass the field-level ACL by invoking the execute_methCVE-2026-108861 · Other software · erpipe-org · reported by VulnCheckMedium 5.3
Odoo MCP 1.0.0 through 1.3.2 contains an information disclosure vulnerability that allows MCP clients to bypass the field-level ACL by invoking the execute_method tool. Attackers or prompt-injected agents can call read or search_read through execute_method naming denied fields to receive their values unredacted.
- Product
- Odoo MCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026mcp-go through 1.2.1 contains a denial of service vulnerability in StreamableHTTPServer.ServeHTTP that allows remote unauthenticated attackers to exhaust memoryCVE-2026-108859 · Other software · mark3labs · reported by VulnCheckHigh 8.7
mcp-go through 1.2.1 contains a denial of service vulnerability in StreamableHTTPServer.ServeHTTP that allows remote unauthenticated attackers to exhaust memory by sending oversized POST bodies. Attackers can send arbitrarily large or many concurrent POST requests, read fully via io.ReadAll before validation, to degrade or OOM-kill the server process.
- Product
- mcp-go
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP servers viCVE-2026-108856 · Other software · UnicomAI · reported by VulnCheckLow 2.3
UnicomAI Wanwu through 0.6.5 contains an authorization bypass vulnerability that allows authenticated users to mint AppKeys bound to other users' MCP servers via POST /v1/appspace/app/key. Attackers supplying a victim's MCP server UUID with appType mcpserver can open MCP sessions and invoke the server's tools using the victim's upstream authentication.
- Product
- Wanwu
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026phpMyFAQ through 4.1.10 contains a missing authorization vulnerability in the MCP server faq_search tool that allows MCP clients to read restricted FAQs becauseCVE-2026-108851 · Other software · thorsten · reported by VulnCheckMedium 4.8
phpMyFAQ through 4.1.10 contains a missing authorization vulnerability in the MCP server faq_search tool that allows MCP clients to read restricted FAQs because Search::searchDatabase() never applies user or group permission checks. Attackers connected to the phpmyfaq:mcp:server can issue search queries to retrieve the full question and answer text of active FAQs restricted to specific users or groups.
- Product
- phpMyFAQ
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026hyper-mcp through 0.8.3 contains an improper signature verification vulnerability that allows attackers to load malicious WebAssembly plugins because cosign_verCVE-2026-108699 · Other software · hyper-mcp-rs · reported by VulnCheckHigh 8.3
hyper-mcp through 0.8.3 contains an improper signature verification vulnerability that allows attackers to load malicious WebAssembly plugins because cosign_verify_args() accepts any signer identity and OIDC issuer by default. Attackers controlling a plugin image reference can sign a malicious image with a free Sigstore keyless certificate to execute plugins with configured host, filesystem, and environment capabilities.
- Product
- hyper-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026hyper-mcp through 0.8.3 contains a signature verification bypass vulnerability in load_wasm in src/wasm/oci.rs that verifies the Cosign signature of a separatelCVE-2026-108698 · Other software · hyper-mcp-rs · reported by VulnCheckHigh 8.3
hyper-mcp through 0.8.3 contains a signature verification bypass vulnerability in load_wasm in src/wasm/oci.rs that verifies the Cosign signature of a separately resolved tag rather than the loaded manifest. Attackers controlling registry responses for the tag can serve an unsigned malicious manifest to the loader and a signed one to Cosign, executing unsigned WebAssembly plugins with configured host capabilities.
- Product
- hyper-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026Abilityai Trinity through 0.9.5 contains a missing authorization vulnerability in the Telegram router that allows agent-scoped MCP API keys to perform human-onlCVE-2026-108756 · Other software · Abilityai · reported by VulnCheckMedium 5.3
Abilityai Trinity through 0.9.5 contains a missing authorization vulnerability in the Telegram router that allows agent-scoped MCP API keys to perform human-only binding operations. Attackers controlling an agent, typically via prompt injection, can send messages through the owner's bot token, replace the binding with their own token, or delete it.
- Product
- trinity
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026Open Computer Use through 1.0.0 on macOS contains an improper case sensitivity handling vulnerability that allows local MCP callers to bypass the password-managCVE-2026-108721 · Other software · iFurySt · reported by VulnCheckMedium 5.8
Open Computer Use through 1.0.0 on macOS contains an improper case sensitivity handling vulnerability that allows local MCP callers to bypass the password-manager denylist using case-variant bundle identifiers. Attackers, including prompt-injected model turns, can pass identifiers like com.1Password.1Password to get_app_state and action tools to read accessibility trees, capture screenshots, and drive unlocked password manager interfaces.
- Product
- open-computer-use
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026mcp-remote 0.8.0 through 0.14.3 contains a cleartext transmission vulnerability in authorizeWithDeviceCode that sends client secrets and receives tokens withoutCVE-2026-108716 · Other software · punkpeye · reported by VulnCheckMedium 6
mcp-remote 0.8.0 through 0.14.3 contains a cleartext transmission vulnerability in authorizeWithDeviceCode that sends client secrets and receives tokens without enforcing HTTPS endpoints. When discovered device authorization and token endpoints are non-loopback http URLs, on-path network attackers can capture the client secret plus issued access and refresh tokens.
- Product
- mcp-remote
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 11, 2026MCP Kotlin SDK through 0.15.0 contains an uncontrolled memory allocation vulnerability that allows remote clients to exhaust server memory because Application.mCVE-2026-108714 · Other software · modelcontextprotocol · reported by VulnCheckHigh 8.7
MCP Kotlin SDK through 0.15.0 contains an uncontrolled memory allocation vulnerability that allows remote clients to exhaust server memory because Application.mcpWebSocket installs Ktor WebSockets without a maxFrameSize limit. Attackers can send small frame headers declaring payloads near 2 GiB over one or a few connections, forcing huge heap allocations and causing denial of service.
- Product
- kotlin-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 10, 2026JeecgBoot through 3.9.5 contains a missing authorization vulnerability that allows any authenticated user to read MCP server configurations because the queryByICVE-2026-108671 · Other software · jeecgboot · reported by VulnCheckHigh 7.1
JeecgBoot through 3.9.5 contains a missing authorization vulnerability that allows any authenticated user to read MCP server configurations because the queryById permission check is commented out. Attackers can obtain record ids from the unguarded /airag/app/queryById endpoint and retrieve MCP endpoint URLs, headers, and outbound authentication tokens.
- Product
- JeecgBoot
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 10, 2026Tabularis through 0.27.0 contains an incorrect authorization vulnerability in the MCP run_query safety gate that allows prompt-injected agents or untrusted MCP CVE-2026-108604 · Other software · TabularisDB · reported by VulnCheckMedium 5.8
Tabularis through 0.27.0 contains an incorrect authorization vulnerability in the MCP run_query safety gate that allows prompt-injected agents or untrusted MCP clients to bypass read-only mode by submitting side-effecting SELECT statements. Attackers can run statements like SELECT setval, nextval, or PostgreSQL query_to_xml with embedded DELETE to modify data without approval prompts.
- Product
- tabularis
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 10, 20261MCP Agent (@1mcp/agent) 0.20.0 through 0.39.0 contains an incorrect authorization vulnerability that allows authenticated clients to bypass OAuth tag-scope enfCVE-2026-108586 · Other software · 1mcp-app · reported by VulnCheckMedium 5.3
1MCP Agent (@1mcp/agent) 0.20.0 through 0.39.0 contains an incorrect authorization vulnerability that allows authenticated clients to bypass OAuth tag-scope enforcement using negated advanced tag-filter expressions. Attackers holding a single-tag token can send a filter like not <granted-tag> to list and invoke tools on backend MCP servers outside their granted scopes.
- Product
- @1mcp/agent
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 10, 2026argocd-mcp (Argo CD MCP Server) through 0.9.0 contains a path traversal vulnerability in the delete_application tool that allows MCP clients to reach unintendedCVE-2026-108585 · Other software · argoproj-labs · reported by VulnCheckMedium 5.3
argocd-mcp (Argo CD MCP Server) through 0.9.0 contains a path traversal vulnerability in the delete_application tool that allows MCP clients to reach unintended API endpoints via unvalidated applicationName values. Attackers or prompt-injected models can supply dot-segment values like ../repositories/ to send authenticated DELETE requests deleting repositories, clusters, or projects within the token's RBAC permissions.
- Product
- argocd-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 10, 2026zotero-mcp 0.10.0 through 0.14.1 contains a server-side request forgery vulnerability that allows attackers to reach internal services because _fetch_embedded_mCVE-2026-108583 · Other software · 54yyyu · reported by VulnCheckLow 2.3
zotero-mcp 0.10.0 through 0.14.1 contains a server-side request forgery vulnerability that allows attackers to reach internal services because _fetch_embedded_metadata fetches URLs without destination validation. Attackers can steer the agent via prompt injection into calling zotero_add_by_url, causing requests to loopback, private, or link-local hosts directly or via redirects, leaking citation meta-tags and error details.
- Product
- zotero-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 10, 2026GenOffice through 0.11.505 contains an incorrect permissions vulnerability in its HTTP MCP server file store that allows local unprivileged users to read uploadCVE-2026-108582 · Other software · genspark-ai · reported by VulnCheckMedium 6.8
GenOffice through 0.11.505 contains an incorrect permissions vulnerability in its HTTP MCP server file store that allows local unprivileged users to read uploaded and generated documents. Attackers can list the world-readable genoffice-mcp-http directory under the system temporary directory to read client uploads and converted outputs, bypassing the HTTP bearer token.
- Product
- GenOffice
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 9, 2026x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP.CVE-2026-107824 · Other software · duty1g · reported by GitHubCritical 9.3
x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Prior to 1.1, x64dbg-MCP Server exposes all MCP debugger tools over HTTP and SSE without authentication while listening on 0.0.0.0 by default. Any unauthenticated network client that can reach the default port, 9094 for x64 or 9095 for x32, can execute arbitrary x64dbg commands, attach to processes by PID, read and write debuggee memory, and write files to arbitrary paths. This issue is fixed in version 1.1.
- Product
- x64dbg-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 9, 2026x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP.CVE-2026-107820 · Other software · duty1g · reported by GitHubMedium 5.3
x64dbg-MCP Server is a native Model Context Protocol (MCP) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Prior to 1.2, src/core/mcp_server.zig parses an unbounded Content-Length value in parseContentLength() and uses it in unchecked usize addition in wsRecv() before token authentication. The server listens on 0.0.0.0 by default in affected versions. An unauthenticated network client can supply a near-maximum Content-Length value to trigger a runtime integer-overflow panic in Debug and ReleaseSafe builds, terminating the entire x64dbg process and its live debugging session. The overflowed value is used only in a comparison, so the impact is limited to denial of service rather than memory corruption or code execution. This issue is fixed in version 1.2.
- Product
- x64dbg-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 8, 2026Improper Input Validation vulnerability in BeamMCP.Schema in ScriptKittyOS beam_mcp allows an MCP client to reach a tool's dispatch function with arguments thatCVE-2026-88257 · Other software · ScriptKittyOS · reported by 6b3ad84c-e1a6-4bf7-a703-f496b71e49dbMedium 5.3
Improper Input Validation vulnerability in BeamMCP.Schema in ScriptKittyOS beam_mcp allows an MCP client to reach a tool's dispatch function with arguments that violate the input schema the server advertised. BeamMCP.Schema.validate/2 checked type, required, additionalProperties, enum and numeric bounds on the top-level arguments object only. Constraints inside nested objects and on array items (items, minItems, maxItems, minLength, maxLength, pattern, nested required, enum and additionalProperties: false) were advertised by tools/list and never checked at tools/call or prompts/get, and keywords outside the enforced subset (oneOf, anyOf, $ref) were advertised and ignored. A host whose dispatch code relies on the schema it declared receives values the schema forbids, such as an out-of-range number or an undeclared key inside a nested object. What the host does with such a value decides the impact. This issue affects beam_mcp: from 0.1.0 before 0.10.1.
- Product
- beam_mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordcna.erlef.orggithub.com
Oct 8, 2026Incorrect Type Conversion or Cast vulnerability in BeamMCP.Server in ScriptKittyOS beam_mcp allows an MCP client's JSON true, false and null tool arguments to rCVE-2026-104634 · Other software · ScriptKittyOS · reported by 6b3ad84c-e1a6-4bf7-a703-f496b71e49dbLow 2.3
Incorrect Type Conversion or Cast vulnerability in BeamMCP.Server in ScriptKittyOS beam_mcp allows an MCP client's JSON true, false and null tool arguments to reach the host's dispatch function as the strings "true", "false" and "nil". After BeamMCP.Schema.validate/2 accepted a value as a boolean, normalize_arguments/2 passed every argument through to_json_value/1, whose atom clause converts true, false and nil to strings. A string is truthy in Elixir, so a host that tests a boolean argument, for example if args.dry_run, takes the opposite branch for false, and a guard such as confirm: false reads as set. The client controls the argument and could send true directly, so the practical impact is limited to hosts whose behaviour on false differs from their behaviour on true, and to any policy layer in front of the server that permits false but refuses true. The same normalisation applies to prompts/get arguments, which exist from 0.5.0. This issue affects beam_mcp: from 0.1.0 before 0.10.1.
- Product
- beam_mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordcna.erlef.orggithub.com
Oct 7, 2026In Splunk MCP Server versions below 1.2.1, Splunk MCP Server could send the Splunk platform authentication token of a user who runs a custom Application ProgramCVE-2026-76286 · Other software · Splunk · reported by psirt@cisco.comMedium 5.3
In Splunk MCP Server versions below 1.2.1, Splunk MCP Server could send the Splunk platform authentication token of a user who runs a custom Application Programming Interface (API) tool to the URL configured for that tool. If another user controls that URL, they could capture the token and use it to access data and perform actions as the user who ran the tool. Successful exploitation requires a user who holds a role that contains the mcp_tool_execute capability to run a custom API tool configured by another user. For more information see Configure the Splunk MCP Server (https://help.splunk.com/en/splunk-enterprise/mcp-server-for-splunk-platform/1.2/configure-the-splunk-mcp-server) and Managing custom tools in Splunk MCP Server (https://help.splunk.com/en/splunk-enterprise/mcp-server-for-splunk-platform/1.2/managing-custom-tools-in-splunk-mcp-server) in the Splunk documentation.
- Product
- Splunk MCP Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 7, 2026Obot 0.26.0 before 0.26.2 contains an authorization bypass vulnerability that allows authenticated users matching any vMCP profile to reach prompts and resourceCVE-2026-105139 · Other software · obot-platform · reported by VulnCheckMedium 5.3
Obot 0.26.0 before 0.26.2 contains an authorization bypass vulnerability that allows authenticated users matching any vMCP profile to reach prompts and resources of ungranted components. Because profiles were enforced only on tools, attackers can access prompts, resources, and resource templates through the vMCP owner's shared component connection.
- Product
- obot
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 7, 2026Obot 0.12.0 before 0.26.2 contains an insufficiently protected credentials vulnerability that allows authenticated users to read static secrets set on MCP catalCVE-2026-105138 · Other software · obot-platform · reported by VulnCheckHigh 7.1
Obot 0.12.0 before 0.26.2 contains an insufficiently protected credentials vulnerability that allows authenticated users to read static secrets set on MCP catalog entries by admins or power users. Basic users granted an entry by access control rules can request GET /api/all-mcps/entries/{entry_id} to obtain plaintext API keys or tokens and abuse them against backend services.
- Product
- obot
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 6, 2026MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients.CVE-2026-104850 · Other software · modelcontextprotocol · reported by GitHubHigh 7.5
MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. Starting in version 1.12.0 and prior to versions 1.31.0 and 2.2.0, the SDK's OAuth client support let the MCP server a client connected to decide which authorization server received the client's OAuth credentials. Stored and pre-provisioned credentials were not bound to the authorization server they belong to. A malicious or compromised MCP server could name its own authorization server in its protected resource metadata. Without any user interaction, the client would send that server the `refresh_token` and `client_secret` stored from an earlier sign-in (1.x), or the configured `client_secret` or signed assertion of a bundled non-interactive provider (1.x and 2.x). Only those applications that use the SDK as an MCP client over HTTP with an `authProvider`: your own `OAuthClientProvider`, or the bundled `ClientCredentialsProvider`, `PrivateKeyJwtProvider`, `StaticPrivateKeyJwtProvider` or (2.x) `CrossAppAccessProvider` and that may connect to an MCP server the owners does not fully trust while holding credentials for a legitimate authorization server are affected. `@modelcontextprotocol
- Product
- typescript-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 6, 2026In the Linux kernel, the following vulnerability has been resolved: Input: cyttsp5 - clamp the HID report size before memcpy The size field comes from the devCVE-2026-98206 · Computers, phones & browsers · Linux · reported by 416baaa9-dc9f-4396-8d5f-8c081fb06d67
In the Linux kernel, the following vulnerability has been resolved: Input: cyttsp5 - clamp the HID report size before memcpy The size field comes from the device and is used as the memcpy() length into response_buf, which is CY_MAX_INPUT bytes.
- 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
Oct 6, 2026Contributor Broken Access Control in WDS MCP Content Manager <= 3.10.4 versions.CVE-2026-39599 · WordPress plugins & themes · reported by PatchstackMedium 4.3
Contributor Broken Access Control in WDS MCP Content Manager <= 3.10.4 versions.
- Affected
- up to 3.10.4
- What to do
- Affects up to 3.10.4. Update the plugin to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Oct 6, 2026IATO MCP: Missing AuthorizationCVE-2026-32582 · WordPress plugins & themes · reported by PatchstackMedium 6.5
Missing Authorization vulnerability in iatoai IATO MCP iato-mcp allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects IATO MCP: from n/a through 1.12.0.
- Product
- IATO MCP
- Affected
- up to 1.12.0
- What to do
- Affects up to 1.12.0. Update IATO MCP to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Oct 5, 2026A caller who can invoke the convert_playwright_script prompt in mcp-k6 can pass a bare file path as the playwright_script argument and receive the contents of aCVE-2026-89039 · Other software · Grafana · reported by security@grafana.comMedium 6.5
A caller who can invoke the convert_playwright_script prompt in mcp-k6 can pass a bare file path as the playwright_script argument and receive the contents of any file readable by the user running the server, including SSH keys and cloud credentials in that user's home directory (path traversal). The working-directory restriction applied to '@'-prefixed paths can also be bypassed with a symbolic link inside the working directory that points outside it.
- Product
- mcp-k6
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 4, 2026Mindio Magic MCP: Insertion of Sensitive Information Into Sent DataCVE-2026-104402 · WordPress plugins & themes · reported by PatchstackMedium 4.3
Insertion of Sensitive Information Into Sent Data vulnerability in farvisun Mindio Magic MCP mindio-magic-mcp allows Retrieve Embedded Sensitive Data.This issue affects Mindio Magic MCP: from n/a through 0.5.6.
- Product
- Mindio Magic MCP
- Affected
- up to 0.5.6
- What to do
- Affects up to 0.5.6. Update Mindio Magic MCP to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Oct 2, 2026Airano MCP Bridge: Missing AuthorizationCVE-2026-32585 · WordPress plugins & themes · reported by PatchstackMedium 6.5
Missing Authorization vulnerability in airano Airano MCP Bridge airano-mcp-bridge allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects Airano MCP Bridge: from n/a through 2.11.0.
- Product
- Airano MCP Bridge
- Affected
- up to 2.11.0
- What to do
- Affects up to 2.11.0. Update Airano MCP Bridge to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Oct 1, 2026A security vulnerability has been detected in modelcontextprotocol mcp-server-fetch and mcp-server-everything up to 2026.6.4.CVE-2026-104120 · Other software · modelcontextprotocol · reported by VulDBMedium 5.5
A security vulnerability has been detected in modelcontextprotocol mcp-server-fetch and mcp-server-everything up to 2026.6.4. Affected is the function fetch_url of the file mcp_server_fetch/server.py of the component Fetch Tool. The manipulation of the argument url/path leads to server-side request forgery. The attack may be initiated remotely. The exploit has been disclosed publicly and may be used. The pull request to fix this issue awaits acceptance.
- Product
- mcp-server-fetch
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 1, 2026Office-PowerPoint-MCP-Server through 2.0.7 contains a path traversal vulnerability that allows MCP callers to write and read files outside the working directoryCVE-2025-71427 · Other software · GongRzhe · reported by VulnCheckHigh 7.6
Office-PowerPoint-MCP-Server through 2.0.7 contains a path traversal vulnerability that allows MCP callers to write and read files outside the working directory by supplying absolute paths or ../ sequences. Attackers can steer an AI agent via prompt injection to abuse save_presentation, open_presentation, or manage_image output_path to overwrite any server-writable file or load external files.
- Product
- Office-PowerPoint-MCP-Server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Oct 1, 2026An argument injection issue in the diff scan operation in AWS security-agent-mcp-server before version 0.2.0 might allow context-dependent threat actors to creaCVE-2026-97662 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 6.9
An argument injection issue in the diff scan operation in AWS security-agent-mcp-server before version 0.2.0 might allow context-dependent threat actors to create, overwrite, or truncate arbitrary files on the host outside the intended workspace directory via a crafted reference value supplied to the diff scan operation. To remediate this issue, users should upgrade to version 0.2.0.
- Product
- security-agent-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordaws.amazon.compypi.org
Oct 1, 2026Subscriber Privilege Escalation in ByteCoreStack – MCP Connector for AI Tools <= 1.2.2 versions.CVE-2026-103068 · WordPress plugins & themes · reported by PatchstackHigh 8.8
Subscriber Privilege Escalation in ByteCoreStack – MCP Connector for AI Tools <= 1.2.2 versions.
- Affected
- up to 1.2.2
- What to do
- Affects up to 1.2.2. Update the plugin to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Oct 1, 2026Obot 0.21.1 through 0.24.1 contains an authorization bypass vulnerability that allows authenticated users to reach MCP servers because the checkUI deny list omiCVE-2026-103758 · Other software · obot-platform · reported by VulnCheckHigh 8.6
Obot 0.21.1 through 0.24.1 contains an authorization bypass vulnerability that allows authenticated users to reach MCP servers because the checkUI deny list omits the /mcp-connect-composite/ route. Basic-role users with a composite MCP ID can proxy requests through mcpGateway.Proxy to invoke tools on MCP servers restricted by Access Control Rules.
- Product
- obot
- 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
Oct 1, 2026ByteCoreStack – MCP Connector for AI Tools: Privilege EscalationCVE-2026-19807 · WordPress plugins & themes · reported by WordfenceHigh 8.8
The ByteCoreStack – MCP Connector for AI Tools plugin for WordPress is vulnerable to Privilege Escalation in all versions up to, and including, 1.2.3 This is due to the `wp_update_user_meta` MCP tool in `execute_tool` gating writes solely with `current_user_can('edit_user', $uid)` — a check that WordPress core's `map_meta_cap` resolves to the `read` primitive when the target user ID matches the caller's own — while enforcing an incomplete meta key blocklist that covers only `user_pass`, `user_activation_key`, and `session_tokens`, leaving the `wp_capabilities` and `wp_user_level` meta keys entirely unprotected. This makes it possible for authenticated attackers with Subscriber-level access and above to elevate their privileges to Administrator by issuing a `wp_update_user_meta` call over the MCP JSON-RPC endpoint with `key=wp_capabilities` and an arbitrary role array such as `{'administrator': true}` targeting their own user ID, causing WordPress to load that account as an Administrator on the next request.
- Product
- ByteCoreStack – MCP Connector for AI Tools
- Affected
- up to 1.2.3
- What to do
- Affects up to 1.2.3. Update ByteCoreStack – MCP Connector for AI Tools 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
Oct 1, 2026AI Engine – The Chatbot, AI Framework & MCP for: Stored Cross-Site ScriptingCVE-2026-96561 · WordPress plugins & themes · reported by WordfenceHigh 7.2
The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the PHP error-log parser (MeowKit_MWAI_Helpers::php_error_logs), the Advisor task (Meow_MWAI_Modules_Advisor::run_advisor), and the Advisor dashboard widget (advisor_metabox): the server-parameter denylist in chat_submit strips only exact key names such as 'model' while convert_keys() later canonicalizes 'model_' back to 'model', allowing an unauthenticated caller to place an attacker-controlled string (including CR/LF) into $query->model; final_checks() throws an Exception whose message embeds that raw string, and the non-streaming, non-admin catch branch writes it to the PHP error log unmodified — creating a forged log line that the plugin's own parser subsequently returns as recent PHP-error content; run_advisor() then appends that content verbatim to the AI prompt (indirect prompt injection — CWE-1427), the returned JSON is stored in the mwai_advisor_data option with no schema validation o
- Product
- AI Engine – The Chatbot, AI Framework & MCP for
- Affected
- up to 3.8.0
- What to do
- Affects up to 3.8.0. Update AI Engine – The Chatbot, AI Framework & MCP for 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
Sep 30, 2026Author Arbitrary File Deletion in WEBO MCP <= 3.0.18 versions.CVE-2026-97242 · WordPress plugins & themes · reported by PatchstackMedium 6.8
Author Arbitrary File Deletion in WEBO MCP <= 3.0.18 versions.
- Affected
- up to 3.0.18
- What to do
- Affects up to 3.0.18. Update the plugin to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Sep 30, 2026Subscriber Broken Access Control in MCP Content Manager Lite <= 1.1.0 versions.CVE-2026-97239 · WordPress plugins & themes · reported by PatchstackMedium 6.5
Subscriber Broken Access Control in MCP Content Manager Lite <= 1.1.0 versions.
- Affected
- up to 1.1.0
- What to do
- Affects up to 1.1.0. Update the plugin to the newest version and check its changelog mentions this fix; if there isn’t one yet, deactivate it until there is.
Sep 29, 2026A vulnerability was identified in 0xshariq github-mcp-server up to 52e764a7d66eac1726fce02ca7bb5a638571801a.CVE-2026-102906 · Other software · 0xshariq · reported by VulDBLow 2.1
A vulnerability was identified in 0xshariq github-mcp-server up to 52e764a7d66eac1726fce02ca7bb5a638571801a. This issue affects the function child_process.exec of the file src/github.ts of the component Git Remove MCP Tool. Such manipulation of the argument File leads to os command injection. The attack can be executed remotely. The exploit is publicly available and might be used. This product implements a rolling release for ongoing delivery, which means version information for affected or updated releases is unavailable. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- github-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Sep 29, 2026metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio (createTCVE-2026-79538 · Other software · reported by MITRECritical 9.8
metatool-ai MetaMCP up to and including 2.4.22 is vulnerable to Code Execution in the internal MCP inspector proxy endpoint GET /mcp-proxy/server/stdio (createTransport, STDIO branch, routers/mcp-proxy/server.ts).
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comtraceforce.ai
Sep 29, 2026metatool-ai MetaMCP through 2.4.22 contains an insecure direct object reference (IDOR) in the MCP transport session dispatch.CVE-2026-79537 · Other software · reported by MITRECritical 9.1
metatool-ai MetaMCP through 2.4.22 contains an insecure direct object reference (IDOR) in the MCP transport session dispatch. The session store (getSession in session-lifetime-manager.ts) is keyed only by the client-supplied mcp-session-id header with no owner, namespace, or endpoint binding, and the per-endpoint authorization middleware validates only the URL endpoint's owner, never the session. An attacker who supplies another tenant's session id " obtained without authentication from GET /metamcp/health/sessions, which discloses active session IDs and namespace UUIDs " can list and execute the victim tenant's private MCP tools and exfiltrate their data using the victim's forwarded credentials.
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordgithub.comtraceforce.ai
Sep 29, 2026mark3labs mcp-filesystem-server v0.11.1 is vulnerable to Directory Traversal due to an improper link resolution in validatePath (filesystemserver/handler/helperCVE-2026-79534 · Other software · reported by MITREMedium 5.9
mark3labs mcp-filesystem-server v0.11.1 is vulnerable to Directory Traversal due to an improper link resolution in validatePath (filesystemserver/handler/helper.go). When filepath.EvalSymlinks returns os.IsNotExist for a dangling symlink, the fallback validates only the parent directory and returns the unresolved path, so write_file (and modify_file, copy_file, move_file, create_directory) follows a pre-existing dangling symlink located inside an allowed directory and creates a file outside the configured allowed directories.
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
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.