context7-docs

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to call Context7 MCP tools (resolve-library-id and get-library-docs) to fetch up-to-date documentation for public third-party libraries (e.g., /microsoft/playwright-python, /googleapis/google-api-python-client) as shown in SKILL.md and examples.md, and then to read and apply that returned content to implement features—meaning untrusted public documentation from external sources can directly influence tool use and actions.