context7

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly resolves and fetches external library documentation using /mcp__context7__resolve-library-id and /mcp__context7__get-library-docs (e.g., /reactjs/react.dev, /vercel/next.js, /mongodb/docs), so the agent ingests and interprets untrusted public third‑party content as part of its workflow.