deep-research

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill connects to Google's official Generative Language API (generativelanguage.googleapis.com), which is a well-known and trusted service provider. All network communications are handled via HTTPS.
  • [SAFE]: Sensitive credentials like the Gemini API key are managed through environment variables or a .env file, adhering to industry standards for secret management and preventing hardcoded credentials.
  • [SAFE]: Local file system activity is limited to a history management system that stores metadata in a standard cache directory (~/.cache/deep-research). This storage is used exclusively for non-sensitive research logs and interaction IDs.
  • [SAFE]: The Python implementation uses standard libraries (httpx, asyncio) and does not contain any suspicious patterns such as dynamic code execution (eval/exec), obfuscated content, or unauthorized subprocess calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 12:53 PM
Security Audit — agent-trust-hub — deep-research