better-ui

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional markdown files providing design guidelines. No malicious code, obfuscated content, or unauthorized data access patterns were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided UI code, which presents a surface for indirect prompt injection. 1. Ingestion points: Frontend code and UI component definitions provided by users (SKILL.md). 2. Boundary markers: No explicit instructions are provided to the agent to ignore instructions embedded within the code it reviews. 3. Capability inventory: The skill provides design feedback and CSS/TSX snippets. It lacks dangerous capabilities like network access, file writing, or shell execution. 4. Sanitization: Input content is treated as text for analysis; no execution or sanitization is performed by the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:38 PM
Security Audit — agent-trust-hub — better-ui