context7

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

• Third-party content exposure detected (high risk: 0.80). This skill directly queries the public Context7 API (e.g., https://context7.com/api/v2/libs/search and /api/v2/context) to fetch external library documentation, so the agent will ingest and read third-party web content that could contain untrusted or user-contributed text.