maintain
Warn
Audited by Snyk on Oct 23, 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 transcripts from a configured corpus directory during the dream/synthesize phase, which are processed by an LLM-based triage judge and synthesis subagents.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata