google-drive

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides Python code snippets for the agent to execute to interact with the Google Drive API and manage OAuth connections.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to gateway.maton.ai, ctrl.maton.ai, and connect.maton.ai to proxy API calls and manage user authentication sessions.
  • [PROMPT_INJECTION]: The skill provides functionality to download and read external file content from Google Drive, which creates a surface for indirect prompt injection if the files contain malicious instructions.
  • Ingestion points: File content retrieved via API endpoints with the alt=media parameter (documented in SKILL.md).
  • Boundary markers: No delimiters or explicit warnings are used to isolate downloaded file content from the agent's core instructions.
  • Capability inventory: The skill can create, update, and delete files on Google Drive, and execute local Python scripts via shell commands.
  • Sanitization: Content retrieved from external sources is processed without validation or filtering for potential injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 12:15 AM
Security Audit — agent-trust-hub — google-drive