gh

Warn

Audited by Snyk on Nov 21, 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 gh workflow exposes outsider-authored GitHub issue and PR text, since commands like gh issue list, gh pr list, and gh issue view/gh pr view return titles and bodies written by anyone who can file issues or PRs on a repo, without the agent first 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 exposes state-changing GitHub operations, including repo deletion, gh api POST mutations, and workflow triggers, but no supplied text establishes explicit irreversible operational loss, so gate 2 fails and the tier 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 21, 2026, 07:45 AM
Issues
2