agent-swarm-pr
Warn
Audited by Snyk on Mar 1, 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 explicitly ingests and acts on untrusted GitHub PR content — e.g., gh pr view/gh pr diff and the webhook-handler parsing github.event.comment.body and invoking npx ruv-swarm/github handle-comment — so arbitrary PR bodies/comments/diffs can directly influence agent behavior.
Audit Metadata