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 -L and git blame when 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/goodstack install that the user runs to obtain gs-find-bad-comments, whose rules then govern the agent; the agoodway publisher 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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 20, 2026, 07:02 PM
Issues
2