single-agent-loop
Warn
Audited by Snyk on Oct 28, 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 reads trace logs and evaluation result logs (
results.jsonl) that record conversation history, agent inputs, and user-facing text from production execution.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata