gdrive

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): No malicious behaviors such as credential exfiltration, persistence, or obfuscation were detected. All commands are standard operations for Google Drive management using the specified 'gog' CLI tool.
  • Indirect Prompt Injection Surface (LOW): Although the skill interacts with external data (file names and metadata from Google Drive), this is an inherent property of its function.
  • Ingestion points: Metadata and file content retrieved via gog drive ls, search, and download commands.
  • Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within Drive content are present in the skill text.
  • Capability inventory: The skill allows file reading, writing, sharing, and URL opening (gog open), which could be leveraged if an agent obeys instructions embedded in Drive metadata.
  • Sanitization: The skill does not explicitly describe sanitization of retrieved metadata before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 08:56 PM