inbox-executive-assistant
Warn
Audited by Snyk on Jul 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: 0.95). Yes—at runtime the required workflow “Pull the inbox” (Gmail connector) returns untrusted email body content and metadata that the agent must read and triage to draft replies, meaning outsider-authored free text from other people’s emails is fed into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata