google-drive-api

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • API Integration via Shell Scripts: The skill leverages local utility scripts (drive_read.sh and drive_search.sh) to interact with the Google Drive API. These scripts use curl for network requests and jq for robust JSON processing, which is standard for this type of integration.- Input Sanitization in Search Queries: The search script includes logic to properly escape single quotes and backslashes before incorporating user input into the Google Drive query expression. This mitigates potential query injection risks within the API's search language.- Security Guidance for Data Ingestion: The SKILL.md file contains a security note regarding retrieved content. It correctly identifies documents and comments as untrusted data and instructs the agent to treat them as inert evidence, reducing the risk of indirect prompt injection.- Standard Execution Environment: All network operations target well-known Google API endpoints (googleapis.com). Authentication is managed through a runtime-injected bearer token, following secure credential management patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 11:17 PM
Security Audit — agent-trust-hub — google-drive-api