gmail-manager

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and read incoming emails via GMAIL_FETCH_EMAILS and GMAIL_GET_THREAD (reading third-party, user-generated email content) and then to perform actions like GMAIL_REPLY_TO_EMAIL and GMAIL_BATCH_MODIFY_MESSAGES, so untrusted email content could contain instructions that materially influence tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 05:15 AM