skill-writing-guide
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation on how to author agent skills following a specific open standard. It contains no scripts, binary assets, or network-active components.\n- [EXTERNAL_DOWNLOADS]: The skill references external URLs for documentation and tool validation (e.g.,
agentskills.io,github.com/agentskills/agentskills). These are informational references to well-known repositories and documentation sites and do not involve silent execution or exfiltration.\n- [COMMAND_EXECUTION]: Thereferences/SPEC_QUICK_REFERENCE.mdfile mentions a validation commandskills-ref validate ./my-skill. This is provided as an example for the user to run manually and is not executed automatically by the agent.
Audit Metadata