better-interface

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a structured workflow for auditing user interfaces across accessibility, layout, writing, typography, color, and UI domains. All operations are local and non-destructive by default.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and analyze untrusted project source code and rendered states.
  • Ingestion points: Project source files (e.g., .tsx, .css) and implementation artifacts identified during the reconnaissance phase.
  • Boundary markers: The instructions do not specify delimiters or system-level instructions to ignore embedded prompts within the files being reviewed.
  • Capability inventory: The skill is authorized to run local verification commands (e.g., linters, tests) and inspect rendered states, but lacks autonomous network or file-writing capabilities unless explicitly requested by the user.
  • Sanitization: No explicit sanitization or filtering of the content being reviewed is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 09:49 AM
Security Audit — agent-trust-hub — better-interface