gpt-taste
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructs the agent to adopt a specific design engineering persona and follow layout rules. These are benign stylistic constraints.
- [SAFE]: External references are limited to well-known and legitimate services, such as
picsum.photosfor placeholder images and standard libraries like GSAP and Phosphor Icons for UI development. - [SAFE]: The 'Python-driven true randomization' section is a prompt engineering technique used to guide the LLM's reasoning process (simulated execution) rather than a request for actual code execution on the host system.
- [SAFE]: No evidence of data exfiltration, credential theft, obfuscation, or persistence mechanisms was found.
Audit Metadata