ulw-research
Warn
Audited by Snyk on Aug 9, 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 required runtime workflow (“Phase 1 — Saturation wave” and “Phase 2 — Expand”) explicitly instructs workers to fetch and ingest outsider-authored web pages and also to perform GitHub searching that can require reading issue/PR text, i.e., the agent ingests free text authored by third parties without any filtering step to select a specific trusted item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata