looking-up-docs

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md explicitly instructs the agent to call Context7 (mcp__context7__get-library-docs / resolve-library-id) to fetch documentation from public repositories (e.g., "/facebook/react", "/vercel/next.js"), meaning it ingests third-party, user-authored docs that the agent reads and could act on.