ai-system-testing
Warn
Audited by Snyk on May 23, 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.md explicitly instructs extracting and HEAD-requesting URLs from model outputs and performing RAG/web_search verification (see "Hallucination Risk Assessment" and tool-call validation examples), which requires fetching and interpreting arbitrary public web content that could be untrusted.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata