ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where untrusted user-supplied input (such as product types or design keywords) is interpolated directly into shell command arguments to invoke an internal search utility.
- Ingestion points: User queries provided in Step 2 and Step 3 of the workflow are passed to the
search.pyscript. - Boundary markers: Absent. The instructions do not define delimiters or warnings to prevent malicious sub-commands from being executed if included in the user query.
- Capability inventory: Shell command execution via
python3is required for the skill to function. - Sanitization: Absent. There are no instructions for the agent to validate or escape the input before passing it to the command line.
- [COMMAND_EXECUTION]: The skill's operational logic relies on executing a local Python script (
skills/ui-ux-pro-max/scripts/search.py) with varying arguments to retrieve design data.
Audit Metadata