skill-supervisor
Warn
Audited by Snyk on Aug 20, 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 runtime workflow reads outsider-authored free text only from the user-provided eval scenario inputs (
evals/pm/scenarios/inputs.jsonl) via the Runner/Modifier, which are not first-party provider content and therefore can contain injected instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata