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-systemas described in the workflow section ofSKILL.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(), andget_style_guide()inSKILL.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_designtool. - 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