deep-research

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes the official @google/genai library to interact with Google's Gemini Interactions API, which is a trusted service.
  • [SAFE]: Instructions include strict cost-governance protocols (the 'Iron Law' and cost warnings), mandating explicit user approval before incurring API costs.
  • [SAFE]: The implementation in deep-research.ts follows standard coding practices for polling and data persistence, with no evidence of obfuscation or unauthorized data access.
  • [SAFE]: No signs of prompt injection, credential exfiltration, or persistence mechanisms were found across the skill documentation and supporting scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 06:29 AM
Security Audit — agent-trust-hub — deep-research