github-cli
Warn
Audited by Snyk on Feb 24, 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's instructions (SKILL.md and linked reference files such as references/issues.md and references/pull-requests.md) explicitly direct using gh commands like
gh issue view,gh pr view,gh api,gh search, andgh gist viewto fetch and read public GitHub issues/PRs/gists and repository content (user-generated/untrusted), which the agent would interpret during workflows and could materially influence actions like triage, review, merges, or workflow triggers.
Audit Metadata