LibreChat
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active.
0Tools
4Findings
34.9kStars
—Downloads
Mar 22, 2026Last Scanned
Findings4
1critical
2high
0medium
1low
0informational
criticalQ3Localhost MCP Service HijackingMCP07-insecure-configT1557
Pattern "(?:express|fastify|koa|hono).*(?:listen|server)(?!.*(?:host[_\s]?(?:check|valid|verify)|helmet))" matched in source_code: "hono/node-server" (at position 8336)
MCP servers binding to localhost must: (1) validate the Host header to prevent DNS rebinding attacks (CVE-2025-49596), (2) set strict CORS origins instead of wildcard '*', (3) require authentication tokens even for local connections, (4) use random high ports instead of predictable defaults. For stdio transport, validate all input at the JSON-RPC level before processing. Consider using Docker MCP Gateway or similar container isolation.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "elliptic@6.6.1" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highL8Version Rollback / Downgrade AttackMCP10-supply-chainAML.T0017
Pattern "["'](?:overrides|resolutions|pnpm\.overrides)["']\s*:\s*\{[^}]*["'][\w@/-]+["']\s*:\s*["'](?:0\.|1\.0|<=|<\d)" matched in source_code: ""overrides": {
"@anthropic-ai/sdk": "0.73.0",
"@librechat/agents": {
"@langchain/anthropic": {
"@anthropic-ai/sdk": "0." (at position 7446)
Use 'npm ci' (not 'npm install') in CI to enforce lockfile integrity. Enable npm audit signatures to verify package provenance. Pin all direct dependencies to exact versions. Use SLSA provenance verification for critical dependencies. Monitor lockfile changes in pull requests with automated diff review. Never use --force or --legacy-peer-deps in production CI.
lowF4MCP Spec Non-ComplianceMCP07-insecure-config
Server fails MCP spec compliance checks: required:server_name; required:server_version; required:protocol_version; recommended:tool_descriptions; recommended:parameter_descriptions
Follow the MCP specification for server metadata. Include server name, version, and protocol version. Provide descriptions for all tools and parameters.
Tools
No tools exposed by this server.
Security Category Deep Dive
Sub-Category Tree · Remediation Roadmap · Attack Stories · Compliance Overlay · ATLAS Techniques · Maturity Model
Prompt Injection
Prompt & context manipulation attacks
69
Maturity
14
Rules
5
Sub-Categories
1
Gaps
64%
Implemented
56
Tests
1
Stories
100%3 rules
Injection via tool descriptions and parameter fields
GAP-001Prompt Injection Coverage GapMissing detection coverage for emerging prompt injection attack variants not addressed by current rules
100%4 rules
Hidden instructions via external content and tool responses
100%2 rules
Context window saturation and prior-approval exploitation
100%3 rules
Payload hiding via invisible chars, base64, schema fields
100%2 rules
Injection via prompt templates and runtime tool output