fetch-library-docs

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches up-to-date documentation from a third‑party MCP (via scripts/fetch-raw.sh calling mcp-client.py with the query-docs tool to Context7) and then passes the returned RAW_TEXT through filter-by-type.sh into the agent's workflow, so the agent will read/interpret content sourced from public third‑party documentation sites.