all-in-one-ui-ux-design

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection via the code audit feature.
  • Ingestion points: The skill is designed to read and analyze user-provided code files (e.g., in .tsx or .html) for accessibility and quality checks, as detailed in SKILL.md and references/web-interface-guidelines.md.
  • Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate the audited code from the agent's control flow.
  • Capability inventory: The skill can generate complex code and UI structures; while no direct system-level or network capabilities are defined in the provided files, the surface for instruction following exists.
  • Sanitization: No mechanisms for filtering or sanitizing the input source code are provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 08:38 PM