coderabbit-interactions
Warn
Audited by Snyk on Feb 16, 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). This skill includes scripts like scripts/export-comments.ts and scripts/reply-to-threads.ts that explicitly export and process PR thread comments (user-generated content from GitHub PRs), meaning the agent would ingest untrusted third‑party content as part of its workflow.
Audit Metadata