swarm-plan
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). SKILL.md requires a “Context7 (library research)” and “Explore” phase where worker-explorer agents perform “web research / external dependencies and APIs,” which commonly ingests public web content or other outsiders’ text into the workers’ LLM context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata