skill-writing-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of Markdown documentation intended to guide developers in writing better agent skills. It does not contain any executable scripts or active components.
- [NO_CODE]: No shell commands, automated scripts, or hidden code blocks were found. The code blocks provided in the rules are static examples for Ruby and TypeScript development meant for teaching purposes.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads or install third-party dependencies.
- [DATA_EXFILTRATION]: No references to sensitive file paths, environment variables, or hardcoded credentials were identified. The skill does not initiate any network requests.
- [PROMPT_INJECTION]: The instructions do not contain attempts to override agent behavior or bypass safety guidelines.
Audit Metadata