parallel-agents
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: 0.70). Pattern 3 explicitly lists "web fetch" alongside KB search and file read, indicating the agents will fetch and read open/public web content (untrusted/user-generated) as part of their workflow, which could enable indirect prompt injection.
Audit Metadata