authoring-skills-and-rules
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a practitioner's guide and reference for authoring other agent skills. It does not contain executable scripts or perform any automated actions other than providing instructional context to the agent.
- [EXTERNAL_DOWNLOADS]: The skill contains references to official documentation and repositories from trusted organizations and well-known services, including Anthropic, OpenAI, GitHub, Microsoft, Cursor, and OpenCode. These references are used for educational purposes and to provide platform-specific context on demand.
- [REMOTE_CODE_EXECUTION]: While the skill mentions tools like
npx skillsandnpx balakitfor distributing skills, these are documented as standard practices for the intended development workflow and are not executed maliciously by the skill itself. - [DYNAMIC_CONTEXT_INJECTION]: The documentation mentions platform features such as
!command(Claude Code) and shell injection in command templates (OpenCode) to explain how those platforms work. The skill itself does not utilize these patterns to execute unauthorized commands.
Audit Metadata