zj-writing-for-agents
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists exclusively of markdown files providing conceptual frameworks and heuristics for agent instruction design. No executable code or scripts are present.
- [SAFE]: There are no references to external URLs, package managers (npm, pip, etc.), or remote resource downloads.
- [SAFE]: No sensitive file access, credential usage, or network operations were identified.
- [SAFE]: The instructions are meta-discussions on prompt engineering (e.g., 'leading words', 'completion criteria') and do not attempt to bypass safety filters or override agent constraints.
Audit Metadata