writing-for-agents

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a pedagogical resource for prompt engineering and agent skill design. It does not perform any automated actions or access sensitive resources.
  • [EXTERNAL_DOWNLOADS]: The documentation contains links to external GitHub repositories for reference and learning. These links point to established developer community resources and represent standard documentation practices.
  • [COMMAND_EXECUTION]: The skill discusses a pattern where bash scripts are used to determine environment state for more deterministic agent behavior. This is documented as a recommendation for other developers and does not involve the execution of untrusted commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 03:28 PM
Security Audit — agent-trust-hub — writing-for-agents