context7

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls ctx7 library and ctx7 docs, which fetches documentation/code examples from Context7’s indexed sources (i.e., public/community-authored package docs and examples) and injects that retrieved free-text/prose into the agent’s LLM context.