arena
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Phase B/C/D/E read outsider-authored free text from the N subagents’ generated outputs (rationales/artifacts) and candidate files into the parent LLM context; those subagents are not the operating user’s own authored content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata