create-skill
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a template and instructional manual for developers to define metadata and directory structures for agent skills. It does not contain any active code, shell commands, or network operations.
- [EXTERNAL_DOWNLOADS]: The documentation provides a link to Anthropic's Claude platform for best practices. As this points to a well-known service for informational purposes, it does not pose a security risk.
- [NO_CODE]: There are no scripts, dependencies, or tool invocations within this skill. It consists entirely of markdown text and examples.
Audit Metadata