pencil

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script to generate design system context, which is a legitimate functional requirement for visual design tasks.
  • Evidence: Execution of python3 .claude/skills/ui-ux-pro-max/scripts/search.py "<product description>" --design-system as described in the workflow section of SKILL.md.
  • [DATA_INGESTION]: The skill processes data from external tool outputs to inform its design decisions, representing a standard indirect prompt injection surface.
  • Ingestion points: Data enters the agent context from the output of search.py, get_guidelines(), and get_style_guide() in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external tool outputs as untrusted data.
  • Capability inventory: The skill can execute local Python scripts and perform complex UI modifications via the batch_design tool.
  • Sanitization: No explicit sanitization or validation of the content fetched from the design system generator or guideline tools is performed before it is used in design operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 08:41 AM
Security Audit — agent-trust-hub — pencil