ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill provides setup instructions for Linux users that include the use of administrative privileges through
sudo apt install python3to install system dependencies. - [COMMAND_EXECUTION]: The core functionality of the skill relies on the agent executing a local Python script (
search.py) to search design domains and generate design systems. - [DYNAMIC_EXECUTION]: The workflow involves constructing shell commands at runtime by interpolating user-provided keywords and product types into the arguments of the
search.pyscript. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface where untrusted data from user requests is ingested and used to execute local commands.
- Ingestion points: User-specified product types, industries, and keywords are used as input for the
search.pyscript in SKILL.md. - Boundary markers: The instructions use double quotes to wrap the query argument in the command template (e.g.,
"<query>"), which provides minimal separation. - Capability inventory: The skill uses subprocess execution to run the
search.pyscript. - Sanitization: There are no instructions or built-in mechanisms described for sanitizing or escaping the user-provided strings before they are executed in the shell.
Audit Metadata