gh-cli-use

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run gh commands that read user-generated GitHub content (e.g., "gh issue list/view", "gh pr view/diff", "gh run view/watch") and then act (create branches, develop issues, merge, rerun workflows), so it ingests untrusted public third‑party content from GitHub that can materially influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 04:52 AM