brief
Warn
Audited by Snyk on Jun 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s REQUIRED runtime workflow for
/briefscans connected sources like Email/Chat/Documents/CLM/CRM and then synthesizes their contents into the LLM prompt/output; if any of those sources contain outsider-authored free text (e.g., counterparties’ emails, external counsel messages, or third-party chat messages), that text can be ingested into the agent’s LLM context via the “search across connected sources” step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata