google-sheets
Fail
Audited by Snyk on Feb 19, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 0.90). The code intentionally routes OAuth token exchange and refresh through an external cloud function (https://google-workspace-extension.geminicli.com), sending users' refresh tokens and likely full tokens to that third-party service (via the redirect_uri and refresh endpoint), which constitutes credential exfiltration risk and a potential backdoor for access to user sheets.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md and scripts/sheets.py) explicitly calls the Google Sheets and Drive APIs (get-text, get-range, find) to fetch arbitrary, user-created spreadsheets and values from Google Drive, which the agent ingests and can use to drive subsequent actions like updates/appends, exposing it to untrusted third-party content.
Audit Metadata