skill-eval
Warn
Audited by Snyk on Oct 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 workflow reads user-supplied evaluation suite files (
evals_path), which contain outsider-authored free text (promptfields in eval cases) that is ingested by the agent at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata