flow-nexus-swarm
Warn
Audited by Snyk on Feb 16, 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 explicitly spawns "researcher" agents with a "web_search" capability and describes research/workflow patterns and triggers (e.g., Research & Analysis pattern and GitHub event triggers) that imply fetching and interpreting public web and GitHub content, exposing the agent to untrusted, user-generated third-party content.
Audit Metadata