gs-find-bad-comments
Warn
Audited by Snyk on Nov 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 required trace in step 2 (SKILL.md:38) has the agent read the commits and pull requests that introduced a comment, and external PR or commit text can be authored by outsiders, which is GitHub PR reading and so medium under the rule.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata