demand-received
Warn
Audited by Snyk on May 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 5 "No silent supplement" and "Source attribution") instructs the agent to run research queries against external legal research tools (e.g., Westlaw, CourtListener, Trellis, Descrybe or "search the web — results will be tagged
[web search — verify]"), so it ingests open/public third‑party content and uses those findings to influence merit assessment and recommended actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata