NYC

google-docs

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: 1.00). The code intentionally routes OAuth authorization/code exchange and refresh operations through a third‑party cloud function (https://google-workspace-extension.geminicli.com), sending refresh tokens/authorization data off‑device — enabling unauthorized remote access and credential exfiltration of users' Google Docs credentials.

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests user-generated Google Docs content via the Google Docs and Drive APIs (see scripts/docs.py get_text / find_docs and the SKILL.md/README get-text and find commands), so arbitrary third‑party document text can be read and could influence the agent's decisions and tool use, enabling indirect prompt injection.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 19, 2026, 05:21 PM