gs-qa-scenarios
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 workflow reads GitHub pull request titles, bodies, commit messages, diffs, and linked tickets via
gh pr view/gh pr diff(and, in run mode, PR comments viagh pr view --comments), all of which outsiders can author or post to without the agent selecting a specific item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill's run modes launch the app and run its verify skill's Launch and Cleanup sections, which may change local or test state, but the supplied text shows no explicit irreversible operational loss, so the answer is low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata