clerk-nextjs-skills
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The MCP server examples (e.g., app/[transport]/route.ts in CLERK_MCP_SERVER_SETUP.md and EXAMPLES.md) call clerk.users.getUser and return JSONified user data and accept arbitrary tool inputs (query-database, upload-file), which exposes untrusted, user-generated third‑party content from Clerk that an AI agent is expected to read/interpret as part of its workflow.
Audit Metadata