deep-research

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The documentation describes a legitimate research automation tool using official APIs. No suspicious command patterns, exfiltration attempts, or obfuscation techniques were identified in the text content.
  • [NO_CODE]: The skill refers to a Python script (scripts/research.py) and a requirements file (requirements.txt) that were not included in the provided file list. The analysis is limited to the SKILL.md documentation.
  • [EXTERNAL_DOWNLOADS]: The instructions mention installing the 'httpx' library via pip. This is a well-known, standard library for HTTP requests and does not pose a security risk in this context.
  • [COMMAND_EXECUTION]: The skill instructions involve running a local Python script with user-supplied arguments. This is the intended functionality of the research tool and uses standard CLI patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:21 PM
Security Audit — agent-trust-hub — deep-research