documentation-lookup

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md "How it works" Steps 1–4) instructs the agent to call the Context7 MCP tools resolve-library-id and query-docs to fetch live, public library documentation (e.g., /vercel/next.js) and to use those fetched docs and code snippets to form answers, so untrusted third‑party documentation could contain instructions that materially influence agent behavior.