meeting-prep-agent
Warn
Audited by Snyk on Jun 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider free text is ingested via step 3 “Read recent communications,” where a news-reader worker summarizes recent client emails (client-authored messages are untrusted and become LLM-readable prose in the agent context).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata