writing-agent-instructions

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation guide for developers on how to structure agent instructions and skills.
  • [SAFE]: It explicitly mandates security best practices under the 'Bake in secrets hygiene' section, instructing users to never hardcode API keys or tokens and to use placeholders instead.
  • [SAFE]: It promotes reliability and safety by instructing agents to 'Never fabricate' and 'Verify before declaring done'.
  • [SAFE]: The mention of local development scripts like 'pnpm sync:workspace-skills' is consistent with the skill's developer-focused scope and does not involve remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:50 AM
Security Audit — agent-trust-hub — writing-agent-instructions