library-research
Warn
Audited by Snyk on Feb 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests documentation from external public sources using context7_get_library_docs and webfetch and even lists GitHub, Stack Overflow, and blog posts as fallbacks, so the agent will read untrusted, user-generated third-party content.
Audit Metadata