ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script ('scripts/search.py') using 'python3' to search design guidelines based on user-provided keywords. It also involves creating and writing to local files in the 'design-system/' directory.
- [PRIVILEGE_ESCALATION]: The skill's setup instructions for Linux users suggest using 'sudo' to install the Python prerequisite.
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a vulnerability surface by interpolating untrusted user input into shell commands and then using the command output to guide further agent behavior. 1. Ingestion points: User-provided product types and keywords are passed to the search script. 2. Boundary markers: The skill does not define specific delimiters for the script's output in the prompt context. 3. Capability inventory: The skill executes shell commands and writes to the local filesystem. 4. Sanitization: No explicit sanitization of user-provided search terms is described.
Audit Metadata