agent-teams
Warn
Audited by Snyk on Feb 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's "Async Handoff" workflow (reference/workflows-detailed.md, Workflows §5) explicitly instructs creating GitHub PRs and tagging the @claude bot so the agent/bot reads PR comments and acts on them, which exposes the agent to untrusted, user-generated content from a public third-party source (GitHub) that can influence subsequent actions.
Audit Metadata