gs-no-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 (low risk: 0.10). The required workflow reads the user's own repository files and diff, plus git history via
git log -Landgit blamewhen tracing thin kills or keeps, and commit messages could in principle come from outside contributors through merged external PRs, but this requires a merge and a conditional history trace, so the attacker cannot force delivery.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The only inbound source is the instructed
npx skills add agoodway/goodstackinstall that the user runs to obtaings-find-bad-comments, whose rules then govern the agent; theagoodwaypublisher is attributed to Lauren Tan via the README and MIT license but is not a recognized first-party organization or signed/digest-verified, so it is common/reputable unofficial and rates medium.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata