no-comments
Fail
Audited by Snyk on Nov 19, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a disclosed comment-cleanup workflow with no sign of malicious intent, but step 5 can delete "do not remove" constraint warnings without encoding them and reports them as open, which is a risky destructive step in unattended runs.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow has the agent read code comments in the caller's files or the git diff against the base branch, which could include outsider-authored comments merged from external contributions, but the agent does not select or fetch a specific outsider-authored item and no outsider can push text into a feed this workflow monitors.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata