gemini-deep-research
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill correctly interacts with the official Google Gemini API (generativelanguage.googleapis.com) using provided credentials.
- [DATA_EXFILTRATION]: The skill transmits research queries to Google's official API endpoints. This is the intended primary purpose of the skill and uses established authentication headers.
- [COMMAND_EXECUTION]: The skill uses local scripts for CLI interaction but does not perform any arbitrary command execution, privilege escalation, or unsafe subprocess spawning.
- [CREDENTIALS_UNSAFE]: The skill follows secure practices by utilizing environment variables and .env files for API key management, rather than hardcoding secrets.
Audit Metadata