skills/shipshitdev/skills/tool-design/Gen Agent Trust Hub

tool-design

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains educational content regarding tool design for AI agents and a utility script (scripts/description_generator.py) for scoring tool descriptions. The Python script uses only standard library modules (json, re, dataclasses, typing) and does not perform any network operations, file system writes, or sensitive data access. The architectural patterns discussed, such as the use of a general-purpose command execution tool, are presented within the context of sandboxed environments and represent legitimate agent design philosophies.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 05:10 AM
Security Audit — agent-trust-hub — tool-design