ai-ethics-tradeoffs
Warn
Audited by Snyk on May 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md "Research-First Workflow" explicitly requires performing web searches for recent incidents, papers, and thought-leader perspectives and to "cite sources — include linked source inline," which requires fetching and interpreting public, user-generated or third‑party web content that can influence the agent's analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata