ce-pr-description
Warn
Audited by Snyk on Apr 25, 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 explicitly fetches and ingests GitHub PR data (e.g., using
gh pr view/gh pr diffin Step 1 PR mode) and reads the PR body (Step 3) — user-generated, untrusted content that the skill interprets (preserving "## Demo/## Screenshots" blocks and using the body/diff to shape the generated PR description), so third-party text can materially influence its outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata