gpt-taste
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of stylistic and architectural instructions for an AI agent to follow when generating frontend code. It does not contain executable malicious payloads or commands.
- [EXTERNAL_DOWNLOADS]: The skill references the use of
picsum.photos, which is a well-known and reputable service for providing placeholder images in web development. - [NODE_PACKAGES]: The instructions recommend the use of standard, reputable frontend libraries including
gsap,@gsap/react, and@phosphor-icons/reactfor the generated code. - [COMMAND_EXECUTION]: The 'Python-driven randomization' mentioned is a prompting technique requiring the AI to simulate logic in its thought process; it does not invoke or require the execution of unauthorized Python scripts on the host machine.
Audit Metadata