context7

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

• Third-party content exposure detected (high risk: 0.80). The skill directly queries the public Context7 API (e.g., https://context7.com/api/v2/libs/search and https://context7.com/api/v2/context) to fetch arbitrary library documentation from the open web, so the agent will ingest untrusted third-party content as part of its workflow.