reply-handling
Warn
Audited by Snyk on Jul 16, 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 required workflow includes an “Audit current reply handling” step that instructs the agent to “pull the last 30-90 days of replies” and categorize them, meaning the LLM would ingest outsider-authored inbound email reply text at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata