context7-efficient

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches public library documentation via Context7 MCP (see scripts/fetch-raw.sh and fetch-docs.sh calling mcp-client.py get-library-docs for IDs like /reactjs/react.dev and /vercel/nextjs.org) and returns filtered snippets into the LLM context, so it consumes open third‑party web content that could embed indirect prompt injections.