MCP Inspector < 0.14.0 UnauthenticatedRemote Code Execution

The MCP inspector is a developer tool for testing and debugging MCP servers. Versions of MCP Inspector below 0.14.1 are vulnerable to remote code execution due to lack of authentication between the Inspector client and proxy, allowing unauthenticated requests to launch MCP commands over stdio. id...

EUVD-2026-33856

A security flaw has been discovered in NousResearch hermes-agent up to 2026.4.23. This affects the function syncanthropicentryfromcredentialsfile of the file agent/credentialpool.py of the component Credential Pool Synchronization. The manipulation results in improper authentication. The attack...

Fake Anthropic Sites Deliver Fileless Infostealer to Claude Code Users

Fake Anthropic websites are being used to target Claude Code users with a fileless infostealer campaign that steals browser credentials and evades detection...

Malicious npm Package Stole Files From Claude AI User Directory via GitHub

Cybersecurity researchers have discovered a new malicious package on the npm registry that comes with information stealing capabilities. According to OX Security, the package, named "mouse5212-super-formatter," is designed to upload files from "/mnt/user-data," a dedicated directory used by...

Claude Mythos AI Identified 10,000+ Software Vulnerabilities in One Month

Anthropic says its Claude Mythos AI identified more than 10,000 software vulnerabilities in one month, including critical flaws in open-source code...

Malicious code in token-me-uk (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 2a058b653e7a491fdf0c9128b4d2d408c2cdac6a1784adc5f02a0975a0e669eb The CLI in cli.mjs reads its API key from process.env.TOKENMEUKAPIKEY, falling back to process.env.OPENAIAPIKEY and then process.env.ANTHROPICAPIKEY...

Anthropic / Microsoft MCP Server-Side Request Forgery

Both Anthropic mcp-server-fetch and Microsoft playwright-mcp suffer from server-side request forgery vulnerabilities by accepting arbitrary URLs passed by the AI agent/client without any allowlist enforcement, IP range blocking, or internal network filtering...

CVE-2026-41863

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

EUVD-2026-31638

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

CVE-2026-41863

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

CVE-2026-41863 LLM-influenced filename used unsanitized in Path.resolve before file write in Spring AI support for Anthropic Skills API

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

CVE-2026-41863 LLM-influenced filename used unsanitized in Path.resolve before file write in Spring AI support for Anthropic Skills API

Spring AI's support for Anthropic's Skills API used LLM-influenced filenames unsanitized in Path.resolve before writing files to disk. This could allow a malicious user to write files outside the intended target directory, including restricted directories. Affected versions: Spring AI: 1.1.0...

CVE-2026-41863

Technical details about the vulnerability (affected component specifics, root cause, exploit scenarios, and remediation) are not provided in the supplied documents. Monitor for updates from Spring.io security advisories.

PT-2026-43006

Name of the Vulnerable Software and Affected Versions Spring AI versions 1.1.0 through 1.1.x Description Support for Anthropic's Skills API uses filenames influenced by the Large Language Model LLM without proper sanitization in the Path.resolve function before writing files to disk. This flaw...

MAL-2026-4398 Malicious code in @jonusnattapong/claudecode (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8a08b3e13079279fb9dce40859dd868b0953bec139996eb7ac915a7dc415b29c Package is a third-party reconstruction of Anthropic's Claude Code CLI that misrepresents itself as the official product. package.json describes itse...

Malicious code in @jonusnattapong/claudecode (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 8a08b3e13079279fb9dce40859dd868b0953bec139996eb7ac915a7dc415b29c Package is a third-party reconstruction of Anthropic's Claude Code CLI that misrepresents itself as the official product. package.json describes itse...

MAL-2026-4457 Malicious code in @tmecontinue/claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 0813d6ca6de1573ab8f99aae08444e589f4c5751931e4b18812140f720b74239 Package self-describes as a 'Reverse-engineered Anthropic Claude Code CLI' and impersonates the legitimate @anthropic-ai/claude-code bin name...

MAL-2026-4563 Malicious code in finkrouter (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector ff852ad2ff69ee287dd37d79ea134314ffca73772068117b819495250ff401f3 The package ships a single heavily-obfuscated cli.obf.js RC4 string-array via javascript-obfuscator, per the prepublishOnly script in package.json...

Malicious code in bingocode (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 7bb3ff21cce9379a60d3ebe3408d8c179e39cfd940eed6deb4afb2f28d852254 package.json declares bin.claude = bin/claude-win.cjs and bin.claude-linux = bin/claude under a non-Anthropic publisher Leanchy. On npm i -g bingocod...

MAL-2026-4497 Malicious code in bingocode (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 7bb3ff21cce9379a60d3ebe3408d8c179e39cfd940eed6deb4afb2f28d852254 package.json declares bin.claude = bin/claude-win.cjs and bin.claude-linux = bin/claude under a non-Anthropic publisher Leanchy. On npm i -g bingocod...