flow-nexus-swarm
Warn
Audited by Snyk on Feb 15, 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 explicitly spawns "researcher" agents with a "web_search" capability and includes a "Research & Analysis" pattern that performs distributed information gathering and analysis of external data (and also accepts triggers like "github_push"/PR events), meaning the agent will fetch and read untrusted public web/GitHub content as part of its workflow.
Audit Metadata