deep-research-swarm
Warn
Audited by Snyk on Apr 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's metadata explicitly lists "google_web_search" as an allowed tool and its "Parallel Search" capability in SKILL.md instructs agents to query multiple databases and perform literature analysis, which requires fetching and interpreting open/public (untrusted/user-generated) web content that can influence agent decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata