testing-strategies
Warn
Audited by Snyk on Jul 28, 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). Source is the user-provided prompt/policy question (e.g., evals/evals.json “prompt”) which is free text ingested at runtime as the “policy packet already in hand” (Step 1), with no requirement to pre-select a specific trusted item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata