ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The SKILL.md and template files include instructions for installing dependencies using commands like 'sudo apt install python3'. These are documented environment setup steps for the user and are consistent with the skill's primary purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill presents an ingestion surface where it takes user requirements to generate design system documentation. The interpolation of untrusted user input into persistent files creates a potential surface for indirect injection if these files are later processed by other agents.
- Ingestion points: User queries and project names are ingested via the search script (scripts/search.py).
- Boundary markers: The generated files use standard Markdown headers and structured sections to delimit content.
- Capability inventory: The script scripts/design_system.py has the capability to create directories and write files to the disk.
- Sanitization: The script performs limited sanitization on user input (replacing spaces with hyphens) when creating project-specific directory paths.
- [DYNAMIC_EXECUTION]: The scripts/design_system.py script constructs file system paths dynamically based on user-supplied project names. This allows the tool to create project-specific folders and write design guidelines, which is its primary documented function.
Audit Metadata