swarm-expert
Warn
Audited by Snyk on Oct 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow involves reading messages and tasks from a multi-agent swarm server (via
read-messages,poll-task,get-tasks), which can contain outsider-submitted free text from other agents or users participating in the swarm.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata