agent-workflow-automation
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: 0.90). The skill explicitly fetches and ingests user-generated repository and pull-request content via the gh CLI (e.g., "PR_DATA=$(gh pr view ...)" and passes that data into ruv-swarm actions which are then used to spawn agents, validate PRs, post comments, create issues, and perform auto-fixes, so third-party content can directly influence agent decisions and actions.
Audit Metadata