inbox-zero
Warn
Audited by Snyk on Jun 22, 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 description indicates it reads email content via IMAP/SMTP; email bodies and messages are authored by external correspondents (outsiders) and would be ingested as free-form text into the agent’s LLM context for categorization/reply drafting.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata