agent-code-review-swarm
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: 0.90). The skill directly fetches and ingests user-generated GitHub PR content (e.g., via "gh pr view ... --json files,...", "gh pr diff 123", and related npx ruv-swarm commands) so the agent will read untrusted third-party PR diffs/bodies/files as part of its review workflow, which could carry indirect prompt-injection payloads.
Audit Metadata