skill-creator
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE] (SAFE): The skill content is limited to instructional documentation and design principles. No indicators of prompt injection, obfuscation, persistence mechanisms, or data exfiltration attempts were found.
- [EXTERNAL_DOWNLOADS] (SAFE): References to external repositories (Anthropic and OpenAI) are for attribution and pattern reference. These match the Trusted GitHub Organizations list and do not involve untrusted remote code execution.
- [COMMAND_EXECUTION] (SAFE): The skill instructions promote the use of 'uv run' and
${CLAUDE_SKILL_ROOT}for managing and executing scripts, which is a recommended secure practice for maintaining environment isolation and reproducible dependency management via PEP 723.
Audit Metadata