skills/ethan-rio/skills/gpt-taste/Gen Agent Trust Hub

gpt-taste

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill instructions define technical and aesthetic guidelines for UI/UX engineering. No malicious patterns such as exfiltration, persistence, or unauthorized command execution were detected.- [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts to influence architectural and stylistic decisions for generated code.
  • Ingestion points: User-provided design requirements (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: None; the skill lacks tools for file system access, network operations, or subprocess execution (SKILL.md).
  • Sanitization: Absent.- [EXTERNAL_DOWNLOADS]: The skill references the well-known picsum.photos service for generating placeholder images.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 10:55 AM
Security Audit — agent-trust-hub — gpt-taste