self-eval
Warn
Audited by Snyk on Aug 21, 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: SKILL.md self-eval runtime workflow reads the current Claude Code conversation history and a local
.self-eval-scores.jsonlfile for anti-inflation, so outsider-authored free text can be ingested via any user/poster-controlled conversation content that the skill evaluates.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata