design-audit

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests untrusted data by scanning project files provided by the user to perform its audit.
  • Ingestion points: The uiux_scan_project tool reads framework, styling, and component data from the target project path.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the scanned files mentioned in the skill definition.
  • Capability inventory: The skill has the capability to read local files, orchestrate multiple agents, and write a summary report (design-audit-report.md).
  • Sanitization: No specific sanitization or validation of the ingested project content is documented.
  • [COMMAND_EXECUTION]: The skill dispatches several specialist agents (e.g., color-analyst, accessibility-auditor) and invokes custom tools like uiux_scan_project and uiux_score_overall. These actions are well-scoped to the primary purpose of conducting a design audit and do not involve arbitrary shell execution.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 08:11 AM
Security Audit — agent-trust-hub — design-audit