writing-agents-md
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidance for context engineering and repository instruction management. No security risks were identified in the workflow or reference materials. The instructions guide the agent to evaluate existing configuration files and move them to appropriate scopes.
- [SAFE]: External links in the README and documentation target well-known and reputable technology services (OpenAI, Anthropic) and established format specifications (agents.md). These references are used for documentation purposes and do not involve remote code execution or data exfiltration.
- [SAFE]: The installation instruction provided in the README uses a standard package runner (npx) and targets the author's own repository (shihyuho/skills), representing standard installation functionality for this skill's ecosystem.
Audit Metadata