fto-triage
Warn
Audited by Snyk on Jul 3, 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). The skill’s runtime workflow includes “Run a preliminary patent search” using connected patent-research integrations (e.g., Solve Intelligence Patents / Google Patents / Espacenet / PatSnap), which fetch and ingest public web/patent-corpus text authored by third parties (patent applicants/assignees) into the agent’s LLM context for claim-charting.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata