authoring-skills
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation and style guide for developing agent skills. It does not contain any executable malicious code, obfuscated content, or unauthorized data access patterns.
- [EXTERNAL_DOWNLOADS]: References official documentation from well-known organizations including Google (Antigravity) and Anthropic. It also points to the author's own GitHub repository for existing skill discovery and potential installation via standard package managers.
- [COMMAND_EXECUTION]: Provides instructions for using Dart-based utility scripts for skill automation. The examples demonstrate the execution of local scripts for defined tasks such as adding release notes or running a linter.
- [INDIRECT_PROMPT_INJECTION]: While the skill defines the structure and behavior of other skills, it does not introduce surfaces for processing untrusted data in an unsafe manner. The guidance for autonomous behavior is presented as a design pattern for task efficiency.
Audit Metadata