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 via gh 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
MEDIUM

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

W013
MEDIUM

Attempt to modify system services in skill instructions.

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