google

Warn

Audited by Snyk on Feb 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: 0.90). The skill explicitly reads user email and file content (e.g., google_gmail_get to read emails and google_drive_get_file to fetch Drive files, plus calendar/event descriptions), which can contain untrusted, user-generated content from external senders and shared files that could carry indirect prompt-injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:17 AM