context7

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

• Third-party content exposure detected (high risk: 0.80). The skill's get-library-docs command fetches and ingests documentation from the Context7 MCP service for arbitrary public libraries (e.g., /vercel/next.js, /mongodb/docs), which pulls open third-party documentation that the agent will read and interpret, exposing it to untrusted external content.