Confidence Check
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and review third‑party documentation and OSS (e.g., "Use WebFetch for documentation URLs", "Use Tavily MCP or WebSearch", and "Search GitHub for examples"), which are open/public untrusted sources that the agent will read and interpret as part of its workflow.
Audit Metadata