ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and execute theui-ux-pro-max-clipackage during initialization. This is a standard installation method for the vendor's command-line tools. - [COMMAND_EXECUTION]: The skill executes a local Python script (
search.py) and various CLI commands (uipro) to query the design database. These commands are executed based on user-provided parameters within the agent's environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied product descriptions and design requirements to generate design systems and recommendations. While this presents an untrusted data ingestion surface, the risk is mitigated by the skill's specific focus on design outputs rather than high-privilege system operations.
- Ingestion points: Product descriptions and UX queries passed to the search script (e.g.,
python3 $SEARCH "..."). - Boundary markers: User inputs are typically wrapped in quotes in the provided command templates.
- Capability inventory: File system writes (via the
--persistflag) and shell command execution of the local search script. - Sanitization: There is no explicit sanitization shown in the instructions, but the scope of actions is limited to generating documentation and design files.
Audit Metadata