git
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill invokes the GitHub CLI to read PRs/comments (e.g., references/worktree-summary.md uses
gh pr list --head ...and references/pr-review-workflow.md usesgh pr view --comments), which fetches user-generated content from public third-party sites that the agent will parse and interpret.
Audit Metadata