gpt-taste

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides specific creative direction and engineering constraints for generating high-quality frontend code. Analysis of the instructions shows no evidence of prompt injection, data exfiltration, or malicious code execution. The 'Python-driven randomization' mentioned is a conceptual instruction for the LLM to follow internally to vary its output and does not involve actual external script execution. All external resources (GSAP, Phosphor Icons, Picsum) are well-known, standard frontend development tools and services.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 05:56 PM
Security Audit — agent-trust-hub — gpt-taste