email-ops
Warn
Audited by Snyk on Jun 20, 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 is an email-operator workflow that, at runtime, reads existing mailbox threads (outsider-authored email body text from other correspondents) before drafting/replying, which the agent would ingest as readable prose into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata