google-workspace

Warn

Audited by Snyk on Feb 24, 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 explicitly searches and downloads user/third-party-generated content from Google Drive and Gmail (e.g., scripts/gdrive_transcript_search.py's get_file_content, scripts/gdrive_search.py and the Gmail/Calendar search reference docs shown in SKILL.md), reads that content as part of its workflow, and uses it in follow-up actions (document generation, folder creation), so untrusted file/email content could indirectly inject instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 24, 2026, 04:22 AM