sentry-pr-code-review
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: 1.00). The skill fetches and parses GitHub PR comments via the gh API (repos/{owner}/{repo}/pulls/{PR_NUMBER}/comments) and explicitly extracts user-generated markdown including "Prompt for AI Agent" blocks, so it ingests untrusted third-party content that could contain indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill runtime calls the GitHub API endpoint "gh api repos/{owner}/{repo}/pulls/{PR_NUMBER}/comments" to fetch Sentry PR comments and explicitly extracts an "🤖 Prompt for AI Agent" block from those comments, which directly controls agent prompts and is required for the skill to operate.
Audit Metadata