inbox-sweep
Warn
Audited by Snyk on Nov 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow searches the user's unread inbox for external emails (Step 1, line 30) and reads full threads (Step 3), so any outsider who emails the user can get text into the agent's context without the agent selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata