deep-research

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Employs standard CLI tools (curl, jq, rg, uuidgen) for API interaction and local data parsing.\n- [EXTERNAL_DOWNLOADS]: Communicates with the DeepAPI service at deepapi.co to perform research, which is a well-known service for this use case.\n- [DATA_EXFILTRATION]: Sends user research queries and the service-specific API key (extracted from ~/.zshrc) to the official endpoint. This is the documented and intended operation of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 03:52 AM
Security Audit — agent-trust-hub — deep-research