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.
934 results · page 8 of 19
Aug 8, 2026A weakness has been identified in HelloGGX shadcn-vue-mcp up to e170e277b94235cde627803277fc8c41103a4d38.CVE-2026-19324 · Other software · HelloGGX · reported by VulDBLow 1.9
A weakness has been identified in HelloGGX shadcn-vue-mcp up to e170e277b94235cde627803277fc8c41103a4d38. Affected by this issue is the function fs.promises.readFile of the file src/server/callback-server.ts. This manipulation of the argument filepath causes path traversal. The attack is restricted to local execution. This product adopts a rolling release strategy to maintain continuous delivery. Therefore, version details for affected or updated releases cannot be specified. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- shadcn-vue-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A security flaw has been discovered in azer react-analyzer-mcp up to 335f2a3585f265e2e88352b59b10d3b478d678b0.CVE-2026-19323 · Other software · azer · reported by VulDBLow 1.9
A security flaw has been discovered in azer react-analyzer-mcp up to 335f2a3585f265e2e88352b59b10d3b478d678b0. Affected by this vulnerability is the function generateProjectDocs of the file src/index.ts of the component analyze-projec. The manipulation of the argument projectName results in path traversal. The attack is only possible with local access. 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
- react-analyzer-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A vulnerability has been found in astralisone rive-mcp-server-core up to db1d0cc4cd52589116360428b7504fd0ca748b3e.CVE-2026-19288 · Other software · astralisone · reported by VulDBLow 1.9
A vulnerability has been found in astralisone rive-mcp-server-core up to db1d0cc4cd52589116360428b7504fd0ca748b3e. This affects an unknown part of the file packages/mcp-server/src/tools/importRiveFile.ts of the component importRiveFile Flow. Such manipulation of the argument libraryId leads to path traversal. The attack needs to be performed locally. 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
- rive-mcp-server-core
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A flaw has been found in abrinsmead mindpilot-mcp 0.5.0.CVE-2026-19287 · Other software · abrinsmead · reported by VulDBLow 1.9
A flaw has been found in abrinsmead mindpilot-mcp 0.5.0. Affected by this issue is some unknown functionality of the component HistoryService. This manipulation of the argument ID causes path traversal. The attack needs to be launched locally. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- mindpilot-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A weakness has been identified in andreahaku llm_memory_mcp up to f11dc8bcff3ff8cf943a2945f99ff3b0bdc8a6d0.CVE-2026-19282 · Other software · andreahaku · reported by VulDBLow 1.9
A weakness has been identified in andreahaku llm_memory_mcp up to f11dc8bcff3ff8cf943a2945f99ff3b0bdc8a6d0. This impacts the function auto.capture of the file src/autolearn/GitHooksManager.ts of the component llm_memory_mcp. Executing a manipulation of the argument hash can lead to command injection. The attack is restricted to local execution. This product does not use versioning. This is why information about affected and unaffected releases are unavailable. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- llm_memory_mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A security flaw has been discovered in adolfosalasgomez3011 slidev-builder-mcp 2.1.0.CVE-2026-19281 · Other software · adolfosalasgomez3011 · reported by VulDBLow 1.9
A security flaw has been discovered in adolfosalasgomez3011 slidev-builder-mcp 2.1.0. This affects the function generateChart of the file src/tools/generateAssets.ts of the component generateAssets Tool. Performing a manipulation of the argument outputDir results in command injection. The attack is only possible with local access. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- slidev-builder-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A vulnerability was identified in MIMICLab mcp-pdf-vision 1.1.0.CVE-2026-19279 · Other software · MIMICLab · reported by VulDBLow 1.9
A vulnerability was identified in MIMICLab mcp-pdf-vision 1.1.0. The impacted element is the function load_pdf of the file src/index.ts. Such manipulation of the argument pdfPath/sessionId leads to command injection. The attack can only be performed from a local environment. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- mcp-pdf-vision
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A security flaw has been discovered in Hulupeep mcp-ui-probe up to 0.2.0.CVE-2026-19270 · Other software · Hulupeep · reported by VulDBLow 1.9
A security flaw has been discovered in Hulupeep mcp-ui-probe up to 0.2.0. Affected is the function get_journey/delete_journey/analyze_journey/usage_stats of the file src/journey/JourneyStorage.ts of the component Journey/Usage. The manipulation of the argument journeyId/filename results in path traversal. The attack requires a local approach. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- mcp-ui-probe
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A vulnerability was identified in abdullah1854 MCPGateway up to 549f494a9e363f40530149de324b8097de424230.CVE-2026-19268 · Other software · abdullah1854 · reported by VulDBLow 2.1
A vulnerability was identified in abdullah1854 MCPGateway up to 549f494a9e363f40530149de324b8097de424230. This impacts the function getUsageByDateRange of the file src/services/claude-usage.ts of the component Claude Usage Range Endpoint. The manipulation of the argument since leads to command injection. The attack can be initiated remotely. The exploit is publicly available and might be used. Continious delivery with rolling releases is used by this product. Therefore, no version details of affected nor updated releases are available. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- MCPGateway
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 8, 2026A vulnerability was found in INQUIRELAB mcp-bridge-api up to b30a82aa1d1d1139e0de846c41c8aadee6e06114.CVE-2026-19263 · Other software · INQUIRELAB · reported by VulDBMedium 6.9
A vulnerability was found in INQUIRELAB mcp-bridge-api up to b30a82aa1d1d1139e0de846c41c8aadee6e06114. The impacted element is an unknown function of the file mcp-bridge.js of the component Servers Endpoint. Performing a manipulation of the argument command/args results in command injection. It is possible to initiate the attack remotely. This product is using a rolling release to provide continious delivery. Therefore, no version details for affected nor updated releases are available. The pull request to fix this issue awaits acceptance.
- Product
- mcp-bridge-api
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 7, 2026Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads.CVE-2026-48039 · Other software · pipeboard-co · reported by GitHubCritical 9.1
Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` unconditionally forwards unauthenticated Streamable HTTP requests to downstream MCP tool handlers without issuing a `401` response, allowing any network-reachable caller to invoke MCP tools without authentication. When no per-request credential is present, tool handlers fall back to the `META_ACCESS_TOKEN` environment variable, and when the downstream Meta Graph API call fails, `api.py:263–269` serialises the raw `httpx` request URL—including the operator's `access_token` as a query parameter—into the JSON-RPC response body, delivering the credential to the unauthenticated caller. Version 1.0.109 fixes the issue.
- Product
- meta-ads-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 6, 2026A vulnerability was detected in NocteDefensor LudusMCP up to 1.0.24.CVE-2026-19047 · Other software · NocteDefensor · reported by VulDBLow 1.9
A vulnerability was detected in NocteDefensor LudusMCP up to 1.0.24. This affects the function executeArbitraryCommand/executeCommand of the file src/ludusMCP/cliWrapper.ts of the component ludus_cli_execute. Performing a manipulation of the argument command/args results in command injection. The attack needs to be approached locally. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- LudusMCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 6, 2026A security vulnerability has been detected in NocteDefensor LudusMCP up to 1.0.24.CVE-2026-19046 · Other software · NocteDefensor · reported by VulDBMedium 4.8
A security vulnerability has been detected in NocteDefensor LudusMCP up to 1.0.24. The impacted element is an unknown function of the file src/tools/ludusEnvironmentGuidesSearch.ts of the component ludus_environment_guides_search. Such manipulation of the argument guide_name leads to path traversal. Local access is required to approach this attack. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- LudusMCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 6, 2026A weakness has been identified in NocteDefensor LudusMCP up to 1.0.24.CVE-2026-19045 · Other software · NocteDefensor · reported by VulDBLow 1.9
A weakness has been identified in NocteDefensor LudusMCP up to 1.0.24. The affected element is the function SecretDialog.showSecretDialog of the file src/utils/secretDialog.ts of the component get_credential_from_user. This manipulation of the argument Description causes command injection. It is possible to launch the attack on the local host. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- LudusMCP
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 6, 2026A flaw has been found in LeeSinLiang godot-mcp 0.1.0.CVE-2026-19044 · Other software · LeeSinLiang · reported by VulDBLow 1.9
A flaw has been found in LeeSinLiang godot-mcp 0.1.0. Affected by this vulnerability is the function executeOperation of the file src/index.ts of the component create_scene/add_node. This manipulation of the argument projectPath causes command injection. The attack needs to be launched locally. The project was informed of the problem early through an issue report but has not responded yet.
- Product
- godot-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 6, 2026A vulnerability has been found in MissionSquad mcp-api up to 1.11.8.CVE-2026-19041 · Other software · MissionSquad · reported by VulDBLow 2.1
A vulnerability has been found in MissionSquad mcp-api up to 1.11.8. The impacted element is the function this.packageService.installPackage of the file src/controllers/packages.ts of the component NPM Package Version Handler. The manipulation leads to command injection. It is possible to initiate the attack remotely. Upgrading to version 1.11.9 is sufficient to resolve this issue. The identifier of the patch is a40f54d4533ba6618e1749383a245900eeb024c1. The affected component should be upgraded.
- Product
- mcp-api
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 6, 2026A flaw has been found in MissionSquad mcp-api up to 1.11.9.CVE-2026-19040 · Other software · MissionSquad · reported by VulDBLow 2.1
A flaw has been found in MissionSquad mcp-api up to 1.11.9. The affected element is an unknown function of the file src/services/dcrClients.ts. Executing a manipulation can lead to server-side request forgery. The attack may be performed from remote. Upgrading to version 1.11.10 is sufficient to fix this issue. This patch is called f068ab4ad6f0907ac7001b995588c2673f11a755. You should upgrade the affected component.
- Product
- mcp-api
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 6, 2026A vulnerability was detected in Kino-Kafkaesque ssh-mcp-server up to 8ebbbb99b26f80ff6162fe00957c6dec73fbc5a5.CVE-2026-19039 · Other software · Kino-Kafkaesque · reported by VulDBLow 1.9
A vulnerability was detected in Kino-Kafkaesque ssh-mcp-server up to 8ebbbb99b26f80ff6162fe00957c6dec73fbc5a5. Impacted is the function ssh_exec of the file src/index.ts of the component SSH Command Handler. Performing a manipulation of the argument host/username results in command injection. The attack requires a local approach. The actual existence of this vulnerability is currently in question. This product adopts a rolling release strategy to maintain continuous delivery. Therefore, version details for affected or updated releases cannot be specified. The project maintainer explains: "The intended threat model is that this MCP server is a local/trusted tool for an agent to execute commands over SSH, so callers already have meaningful execution capability through the exposed shell."
- Product
- ssh-mcp-server
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 6, 2026A security vulnerability has been detected in MonomythDevelopment la-forge-mcp 1.0.0.CVE-2026-19038 · Other software · MonomythDevelopment · reported by VulDBLow 2.1
A security vulnerability has been detected in MonomythDevelopment la-forge-mcp 1.0.0. This issue affects the function screenshotElement of the file src/index.ts of the component screenshot_element Tool. Such manipulation of the argument output_name leads to path traversal. The attack can be executed remotely. Upgrading to version 1.1.1 is capable of addressing this issue. The name of the patch is 1102172c9adec4a619e241efd6bfb74f5b1f4332. Upgrading the affected component is advised. The vendor was contacted early, responded in a very professional manner and quickly released a fixed version of the affected product.
- Product
- la-forge-mcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 5, 2026FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP).CVE-2026-67531 · Other software · agentfront · reported by GitHubCritical 9.3
FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP). Prior to 1.5.7, the sandboxed codecall:execute tool exposes live host Zod schema instances to the script via getTool(), and because Zod v4 defines _zod as a non-configurable, non-writable own property, the ECMAScript Proxy invariants force the security membrane to hand back the raw host object, letting a script reach _zod.constr.constructor (the host Function constructor) and execute arbitrary code in the server process. A single tools/call is sufficient to escape the sandbox and achieve remote code execution as the server user, exposing everything the process holds such as OAuth client secrets, JWT_SECRET, session keys, database credentials, and cloud instance metadata. Because the framework's DEFAULT_AUTH_OPTIONS is public mode, an unconfigured server serves this to unauthenticated callers, and on authenticated servers an indirect prompt injection in tool output or fetched content can trigger it without a human attackerThis issue is fixed in version 1.5.7.
- Product
- frontmcp
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 5, 2026Incorrect authorization in the aggregation pipeline tool in Amazon AWS Labs DocumentDB MCP Server before 1.0.12 might allow an authenticated MCP client to perfoCVE-2026-18954 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 5.7
Incorrect authorization in the aggregation pipeline tool in Amazon AWS Labs DocumentDB MCP Server before 1.0.12 might allow an authenticated MCP client to perform inappropriate write operations on the connected database via write-capable aggregation pipeline stages that bypass the read-only mode enforcement logic. To remediate this issue, users should upgrade to version 1.0.12 or later.
- Product
- documentdb-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.comgithub.com
Aug 5, 2026Improper limitation of a pathname to a restricted directory in the get_resource tool in Amazon awslabs.aws-transform-mcp-server 0.1.0 through 0.1.4 might allow CVE-2026-18953 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5Medium 6.3
Improper limitation of a pathname to a restricted directory in the get_resource tool in Amazon awslabs.aws-transform-mcp-server 0.1.0 through 0.1.4 might allow a context-dependent actor to write arbitrary files outside the intended working directory via the savePath parameter. To remediate this issue, users should upgrade to version 0.1.5 or later.
- Product
- aws-transform-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.comgithub.com
Aug 5, 2026IBM Langflow OSS 1.0.0 through 1.10.3 Langflow allows remote authenticated attackers to bypass localhost-only restrictions and write arbitrary MCP server configCVE-2026-9077 · Other software · IBM · reported by psirt@us.ibm.comHigh 8.5
IBM Langflow OSS 1.0.0 through 1.10.3 Langflow allows remote authenticated attackers to bypass localhost-only restrictions and write arbitrary MCP server configurations to IDE configuration files on the host system.
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 5, 2026IBM Langflow OSS 1.0.0 through 1.10.3 contain an authentication bypass vulnerability in the Model Context Protocol (MCP) composer endpoint when mcp_composer_enaCVE-2026-8446 · Other software · IBM · reported by psirt@us.ibm.comHigh 7.5
IBM Langflow OSS 1.0.0 through 1.10.3 contain an authentication bypass vulnerability in the Model Context Protocol (MCP) composer endpoint when mcp_composer_enabled=true (default) and projects are configured with auth_type=oauth .
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 5, 2026A vulnerability in the Extensible Messaging Client Protocol (XMCP), also referred to as the External Client protocol, of Cisco IOS Software and Cisco IOS XE SofCVE-2026-20301 · Network & remote access · Cisco · reported by psirt@cisco.comHigh 8.6
A vulnerability in the Extensible Messaging Client Protocol (XMCP), also referred to as the External Client protocol, of Cisco IOS Software and Cisco IOS XE Software could allow an unauthenticated, remote attacker to cause a denial of service (DoS) condition on an affected device. This vulnerability is due to improper handling of malformed XMCP packets. An attacker could exploit this vulnerability by sending a malformed XMCP packet to an affected device. A successful exploit could allow the attacker to cause the affected device to reload unexpectedly, resulting in a DoS condition. The attacker does not need the XMCP client username to exploit this vulnerability.
- Product
- Cisco IOS XE Software
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordsec.cloudapps.cisco.com
Aug 5, 2026IBM Langflow OSS 1.0.0 through 1.10.3 Langflow could allow an authenticated attacker to read, modify, or expose sensitive host files via Docker-based MCP serverCVE-2026-17626 · Other software · IBM · reported by psirt@us.ibm.comHigh 8.8
IBM Langflow OSS 1.0.0 through 1.10.3 Langflow could allow an authenticated attacker to read, modify, or expose sensitive host files via Docker-based MCP servers due to incomplete filtering of dangerous Docker volume-mount and device-mapping arguments.
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 5, 2026tinyobjloader-c's tinyobj_parse_and_index_mtl_file (tinyobj_loader_c.h) reads each line of a .mtl material file into a fixed 4096-byte stack buffer via memcpy(lCVE-2026-71266 · Other software · syoyo · reported by 309f9ea4-e3e9-4c6c-b79d-e8eb01244f2cHigh 7.8
tinyobjloader-c's tinyobj_parse_and_index_mtl_file (tinyobj_loader_c.h) reads each line of a .mtl material file into a fixed 4096-byte stack buffer via memcpy(linebuf, p, p_len), guarded only by . The identical vulnerable pattern is duplicated in a second function in the same file.
- Product
- tinyobjloader-c
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Aug 3, 2026Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server (awslabs.amazon-mq-mcp-server) before 2.0.24 may CVE-2026-18655 · Other software · AWS · reported by ff89ba41-3aa1-4d27-914a-91399e9639e5High 7.1
Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server (awslabs.amazon-mq-mcp-server) before 2.0.24 may allow a remote unauthenticated actor (via prompt injection) to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent to a crafted endpoint controlled through a broker hostname introduced in the MCP client context. To remediate this issue, users should upgrade to version 2.0.24.
- Product
- amazon-mq-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.comgithub.com
Aug 2, 2026ArcadeDB versions before 26.7.3 fail to bind the authenticated principal in the MCP HTTP transport, causing all engine permission checks to silently pass as no-CVE-2026-68578 · Other software · ArcadeData · reported by VulnCheckHigh 7.7
ArcadeDB versions before 26.7.3 fail to bind the authenticated principal in the MCP HTTP transport, causing all engine permission checks to silently pass as no-ops. Non-root MCP-allowed users can perform arbitrary database writes, DDL, schema mutations, and execute arbitrary JavaScript code via the query tool.
- 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 2, 2026ArcadeDB versions before 26.7.3 contain an information disclosure vulnerability in the MCP get_server_settings tool that leaks the arcadedb.ha.clusterToken in cCVE-2026-67357 · Other software · ArcadeData · reported by VulnCheckHigh 7.7
ArcadeDB versions before 26.7.3 contain an information disclosure vulnerability in the MCP get_server_settings tool that leaks the arcadedb.ha.clusterToken in cleartext. Attackers with MCP access can retrieve the cluster token and use it with X-ArcadeDB-Cluster-Token and X-ArcadeDB-Forwarded-User headers to impersonate root and achieve full server compromise.
- 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 1, 2026better-auth versions before 1.6.11 contain insecure cryptographic defaults in the oidcProvider and mcp plugins that advertise the none algorithm and accept plaiCVE-2026-67336 · Other software · better-auth · reported by VulnCheckCritical 9.4
better-auth versions before 1.6.11 contain insecure cryptographic defaults in the oidcProvider and mcp plugins that advertise the none algorithm and accept plain PKCE by default. Attackers can exploit algorithm negotiation to accept unsigned tokens or intercept authorization codes when PKCE plain is used instead of the required S256 method.
- Product
- better-auth
- 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 1, 2026AI Engine – The Chatbot, AI Framework & MCP for: Cross-Site Request ForgeryCVE-2026-15988 · WordPress plugins & themes · reported by WordfenceHigh 8.8
The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Cross-Site Request Forgery in all versions up to, and including, 3.6.5 This is due to missing or incorrect nonce validation on the reauth_for_authorize function. This makes it possible for unauthenticated attackers to create new administrator accounts with attacker-supplied credentials via a CSRF-based REST authentication bypass, granted they can trick a site administrator into performing an action such as clicking on a link. This bypass can be combined with WordPress's ?_method=POST method-override support to convert a top-navigation GET request into an authenticated POST to the REST users endpoint, requiring no existing account on the attacker's part.
- Product
- AI Engine – The Chatbot, AI Framework & MCP for
- Affected
- up to 3.6.5
- What to do
- Affects up to 3.6.5. 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
Jul 31, 2026gemini-bridge is a lightweight MCP server bridging AI agents to Google's Gemini AI via the official CLI.CVE-2026-54785 · Other software · eLyiN · reported by GitHubMedium 6.2
gemini-bridge is a lightweight MCP server bridging AI agents to Google's Gemini AI via the official CLI. From 1.0.0 until 1.3.1, consult_gemini_with_files in inline mode read any file path supplied in the files argument without confining it to the working directory, then forwarded the contents to the Gemini CLI. Because the caller also controls query, the file contents are echoed back through the Gemini round-trip (and sent to Google), making this an arbitrary local file read. This issue is fixed in version 1.3.1.
- Product
- gemini-bridge
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 30, 2026An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0.CVE-2026-14541 · Computers, phones & browsers · Google · reported by cve-coordination@google.comHigh 8
An authentication bypass and audience confusion vulnerability exists in the Google OAuth provider component of Google mcp-toolbox version 1.4.0. When a Google authService is initialized with mcpEnabled: true but lacks an explicitly defined audience or clientId, the ValidateMCPAuth pipeline for opaque tokens skips audience validation entirely. As a result, the toolbox will accept any valid Google OAuth access token—even those minted for unrelated ecosystem applications—granting unauthorized clients access to protected tools and data backends.
- Product
- mcp-toolbox
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 30, 2026A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0.CVE-2026-14540 · Computers, phones & browsers · Google · reported by cve-coordination@google.comHigh 8
A Server-Side Request Forgery (SSRF) vulnerability exists in the generic HTTP source and tool components of Google mcp-toolbox versions 0.3.0 through 1.4.0. While the toolbox implements baseline input sanitization for user-controlled parameters, the underlying HTTP client (internal/sources/http/http.go) fails to safely regulate request redirection boundaries. Specifically, the client is initialized without a restrictive CheckRedirect policy hook and lacks target IP validation. An attacker or a malicious data-driven prompt can supply a crafted path parameter that triggers an open redirect or a direct destination swap on the target backend, coercing the mcp-toolbox into blindly following the redirection and making unauthorized requests to internal or arbitrary external endpoints.
- Product
- mcp-toolbox
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 30, 2026An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unautheCVE-2026-14539 · Computers, phones & browsers · Google · reported by cve-coordination@google.comMedium 6.6
An allocation of resources without limits vulnerability in the HTTP handler component of Google mcp-toolbox versions up to and including 1.4.0 allows an unauthenticated attacker to cause a denial of service (DoS). The /mcp endpoint handler reads incoming payloads directly into system memory using an unrestricted buffer loop (io.ReadAll) without applying defensive constraints such as http.MaxBytesReader or pre-read Content-Length enforcement. By submitting a single, massive HTTP request body, an attacker can linearly consume available host memory until the runtime process is terminated by an Out-Of-Memory (OOM) error.
- Product
- mcp-toolbox
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 30, 2026An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.CVE-2026-14538 · Computers, phones & browsers · Google · reported by cve-coordination@google.comMedium 5.7
An improper authorization and security-boundary bypass vulnerability in the bigquery-execute-sql tool component of Google mcp-toolbox versions 0.16.1 through 1.4.0 allows an authenticated attacker to bypass allowedDatasets validation checks. The toolbox relies on the BigQuery dry-run API to enforce dataset restrictions, but due to a fail-open logic flaw, it bypasses validation when the API returns an empty array for specialized constructs. This allows the attacker to extract structural DDL schemas for explicitly excluded datasets via INFORMATION_SCHEMA, and access downstream federated row data via EXTERNAL_QUERY connections.
- Product
- mcp-toolbox
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 30, 2026Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to iCVE-2026-14537 · Computers, phones & browsers · Google · reported by cve-coordination@google.comHigh 8.1
Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-api flag is active.
- Product
- mcp-toolbox
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 30, 2026IBM Langflow OSS 1.0.0 through 1.10.1 are vulnerable to unauthenticated remote code execution via environment variable injection in the MCP (Model Context ProtCVE-2026-12940 · Other software · IBM · reported by psirt@us.ibm.comCritical 9.8
IBM Langflow OSS 1.0.0 through 1.10.1 are vulnerable to unauthenticated remote code execution via environment variable injection in the MCP (Model Context Protocol) stdio launcher. The vulnerability exists in src/lfx/src/lfx/base/mcp/util.py where the DANGEROUS_ENV_VARS blocklist fails to include SHELLOPTS , BASHOPTS , and PS4 environment variables.
- Product
- Langflow OSS
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 29, 2026Insufficient policy enforcement in WebMCP in Google Chrome prior to 151.0.7922.72 allowed a remote attacker to bypass same origin policy via a crafted HTML pageCVE-2026-17854 · Computers, phones & browsers · Google · reported by chrome-cve-admin@google.comMedium 6.5
Insufficient policy enforcement in WebMCP in Google Chrome prior to 151.0.7922.72 allowed a remote attacker to bypass same origin policy via a crafted HTML page. (Chromium security severity: Medium)
- Product
- Chrome
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Full record and what to do →NVD recordchromereleases.googleblog.comissues.chromium.org
Jul 29, 2026MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients.CVE-2026-67432 · Other software · modelcontextprotocol · reported by GitHubHigh 7.5
MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem reads and parses an entire JSON-RPC POST body without a size limit, allowing an unauthenticated remote attacker to exhaust process memory. This issue is fixed in version 0.23.0.
- Product
- ruby-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 29, 2026MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients.CVE-2026-67431 · Other software · modelcontextprotocol · reported by GitHubHigh 8.3
MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem does not bind a session ID to a session owner, allowing an attacker with a stolen session ID to send tools/call requests that execute in the victim's session. This issue is fixed in version 0.23.0.
- Product
- ruby-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 29, 2026MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients.CVE-2026-67430 · Other software · modelcontextprotocol · reported by GitHubMedium 5.3
MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem does not expire sessions by default, so repeated initialize requests retain unbounded ServerSession objects and can exhaust process memory. This issue is fixed in version 0.23.0.
- Product
- ruby-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 29, 2026MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients.CVE-2026-63119 · Other software · modelcontextprotocol · reported by GitHubMedium 6.2
MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StdioTransport and MCP::Client::Stdio in the mcp gem use IO#gets without a byte limit, allowing a peer that sends data without a newline to exhaust process memory. This issue is fixed in version 0.23.0.
- Product
- ruby-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 29, 2026MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients.CVE-2026-63118 · Other software · modelcontextprotocol · reported by GitHubMedium 6.9
MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem does not validate the HTTP Host or Origin request headers, which allows a malicious browser page to use DNS rebinding to reach a locally running MCP server and invoke exposed tools. This issue is fixed in version 0.23.0.
- Product
- ruby-sdk
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 29, 2026In consul-mcp-server, versions 0.1.0 up to 0.1.3 did not restrict how the Consul backend address was supplied, allowing a connected client to override the serveCVE-2026-16328 · Other software · HashiCorp · reported by security@hashicorp.comHigh 8.6
In consul-mcp-server, versions 0.1.0 up to 0.1.3 did not restrict how the Consul backend address was supplied, allowing a connected client to override the server's configured Consul address via a request header. This may allow a malicious client to redirect the server's Consul API traffic to an attacker-controlled endpoint, potentially exfiltrating the Consul token configured on the server. This vulnerability, CVE-2026-16328, is fixed in consul-mcp-server 0.1.4.
- Product
- Tooling
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 29, 2026In consul-mcp-server, versions 0.1.0 up to 0.1.3 did not properly isolate session state in stateless mode, which may allow one client's Consul authentication toCVE-2026-16326 · Other software · HashiCorp · reported by security@hashicorp.comCritical 10
In consul-mcp-server, versions 0.1.0 up to 0.1.3 did not properly isolate session state in stateless mode, which may allow one client's Consul authentication token to be used for subsequent requests from other clients. This vulnerability (CVE-2026-16326) is fixed in consul-mcp-server 0.1.4.
- Product
- Tooling
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 28, 2026The terraform-mcp-server before version 1.1.0 is vulnerable to a cross-tenant credential reuse issue in the streamable-HTTP stateless transport mode that may alCVE-2026-16498 · Other software · HashiCorp · reported by security@hashicorp.comCritical 10
The terraform-mcp-server before version 1.1.0 is vulnerable to a cross-tenant credential reuse issue in the streamable-HTTP stateless transport mode that may allow one user's Terraform token to be used to execute tool calls on behalf of subsequent users. This vulnerability, CVE-2026-16498, is fixed in terraform-mcp-server 1.1.0.
- Product
- Tooling
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 28, 2026The terraform-mcp-server before version 1.1.0 is vulnerable to an authorization bypass in the streamable-HTTP stateful transport mode that may allow a user who CVE-2026-16496 · Other software · HashiCorp · reported by security@hashicorp.comHigh 8.9
The terraform-mcp-server before version 1.1.0 is vulnerable to an authorization bypass in the streamable-HTTP stateful transport mode that may allow a user who obtains another user's MCP session ID to have their tool calls executed using that user's Terraform credentials. This vulnerability, CVE-2026-16496, is fixed in terraform-mcp-server 1.1.0.
- Product
- Tooling
- What to do
- Apply the vendor’s update. The NVD record links to the advisory.
Jul 28, 2026The terraform-mcp-server before version 1.1.0 is vulnerable to a server-side request forgery issue in the streamable-HTTP transport that may allow an unauthentiCVE-2026-14869 · Other software · HashiCorp · reported by security@hashicorp.comHigh 8.6
The terraform-mcp-server before version 1.1.0 is vulnerable to a server-side request forgery issue in the streamable-HTTP transport that may allow an unauthenticated remote client to redirect the server's Terraform API requests, and the server-side authorization token, to an attacker-controlled endpoint. This vulnerability, CVE-2026-14869, is fixed in terraform-mcp-server 1.1.0.
- Product
- Tooling
- 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.