PostHog
Integrates with PostHog product analytics to query analytics data, manage feature flags, create insights, run experiments, and track errors.
0Tools
9Findings
32.1kStars
—Downloads
Mar 22, 2026Last Scanned
Findings9
3critical
4high
1medium
1low
0informational
criticalQ11Code Suggestion Poisoning via MCPMCP01-prompt-injectionAML.T0054.001
Pattern "(?:postinstall|preinstall|prepare).*(?:script|hook|command).*(?:inject|add|modify)" matched in source_code: "preinstall scripts for, add" (at position 6196)
MCP tool outputs flowing into IDE code suggestion contexts must be sanitized. Implement output content policies that: (1) strip hidden Unicode characters (zero-width, RTL override, tag characters), (2) detect embedded instructions targeting AI code assistants, (3) validate code blocks against security patterns before they enter the suggestion pipeline, (4) never include shell commands in tool outputs without explicit [COMMAND] markers visible to the user. Reference: IDEsaster (Dec 2025), arXiv 2509.22040.
criticalC2Path TraversalMCP05-privilege-escalation
Pattern "\.\./\.\." matched in source_code: "../.." (at position 1375)
Use path.resolve() to canonicalize paths, then verify the result starts with the intended base directory. Reject any input containing '..', null bytes, or encoded variants. Never concatenate user input into file paths.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 5375)
MCP bridge packages (mcp-remote, mcp-proxy, @modelcontextprotocol/sdk, fastmcp) are high-value supply chain targets — CVE-2025-6514 (CVSS 9.6) in mcp-remote affected 437,000+ installs. Always pin exact versions (no ^ or ~ ranges). Use lockfiles (package-lock.json, pnpm-lock.yaml, uv.lock). Never run `npx mcp-remote` without version pinning. Verify package integrity with `npm audit` or `pip-audit` before deployment. Reference: CVE-2025-6514, OWASP ASI04.
highL14Hidden Entry Point MismatchMCP10-supply-chainAML.T0017
Pattern "["']browser["']\s*:\s*\{[^}]*["'](?:fs|child_process|crypto|net|http|os|path)["']\s*:\s*["'](?!false)" matched in source_code: ""browser": {
"path": "" (at position 412)
Ensure all entry point fields (main, module, exports, bin, browser) reference the same code paths. Do not block access to ./package.json in the exports map. Audit bin fields for commands that shadow system utilities. Use consistent entry points across import/require conditions. Verify that conditional exports don't serve different code to different contexts.
highC11ReDoS VulnerabilityMCP07-insecure-config
Pattern "\([^)]*[*+][^)]*\)[*+]" matched in source_code: "(**/.sqlx/**)*" (at position 4312)
Never compile user-supplied strings as regexes. Use a safe regex library (re2, node-re2) for all user-controlled pattern matching — they run in linear time. Bound all input lengths before regex application. Use static analysis tools (safe-regex, vuln-regex-detector) to audit existing patterns.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "playwright@1.45.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highK19Missing Runtime Sandbox EnforcementMCP07-insecure-configAML.T0054
Pattern "(run[_\s-]?as[_\s-]?root|EUID.*0|uid.*0)(?!.*(?:drop|setuid|seteuid|change.?user))" matched in source_code: "uid": "^10.0.0" (at position 3473)
Run MCP servers in sandboxed containers with: (1) No --privileged flag, (2) Minimal Linux capabilities (drop ALL, add only needed), (3) Read-only root filesystem, (4) Non-root user, (5) Seccomp/AppArmor profiles enabled, (6) No host mounts except data volumes. CoSAI warns containers alone are insufficient — add seccomp profiles. Required by CoSAI MCP-T8 and ISO 27001 A.8.22.
mediumE1No Authentication RequiredMCP07-insecure-config
Server does not require authentication for connections
Require authentication for MCP server connections. Use API keys, bearer tokens, or OAuth to authenticate clients before allowing tool enumeration or invocation.
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