swarm-advanced
Warn
Audited by Snyk on Mar 4, 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's Research Workflow (Phase 1) explicitly spawns a "Web Researcher" and calls mcp__claude-flow__parallel_execute with tasks such as "web-search" and "academic-search" to gather public articles/datasets that are ingested and used to drive analysis and orchestration, meaning untrusted third‑party web content can influence tool actions and decisions.
Audit Metadata