ai-evals
Warn
Audited by Snyk on Sep 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow involves reading and evaluating external content, specifically indirect prompt injection risks associated with ingesting retrieved text or tool output in tool-using agents as detailed in safety-redteam-eval.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata