orchestrating-swarms
Warn
Audited by Snyk on May 14, 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 spawns research/guide agents that use WebFetch/WebSearch and accept external URLs (e.g., "claude-code-guide" lists WebFetch/WebSearch, the Design Agent example "Compare with Figma at [URL]", and Pattern 4's Research → use research.content in a follow-on Task), so the agent is expected to fetch and interpret open-web or user-provided content and then act on it, enabling indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata