swarm-developer-guide
Warn
Audited by Snyk on Mar 2, 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.md workflow explicitly tells the agent to "Read each GitHub issue for the detailed finding" when fixing review feedback, meaning it will fetch and act on user-generated, public GitHub content that can directly change its fixes and tool actions.
Audit Metadata