skill-authoring
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill package consists exclusively of Markdown documentation and JSON metadata. No executable scripts (.py, .js, .sh) or binary files are present.
- [SAFE]: All external references point to legitimate and trusted sources, including official Anthropic documentation, the Model Context Protocol website, and established technical standards (YAML, CommonMark, SemVer).
- [SAFE]: The skill provides defensive security guidance in
references/maint-audit-security.md, instructing users on how to detect malicious patterns such as data exfiltration and credential theft in other skills. - [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data access were found. The content is focused on improving skill discovery, token efficiency, and trigger reliability.
Audit Metadata