ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONPRIVILEGE_ESCALATION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute a local Python script (
skills/ui-ux-pro-max/scripts/search.py) with various arguments to generate design recommendations. - [PRIVILEGE_ESCALATION]: The documentation includes shell commands using
sudo apt installto assist the user or agent in setting up the Python environment if it is missing. - [DYNAMIC_EXECUTION]: The skill implements a persistence pattern where it writes design rules to files (e.g.,
design-system/MASTER.mdanddesign-system/pages/dashboard.md) and subsequently instructs the agent to read these files to govern code generation. This creates a feedback loop where dynamically generated content defines future agent behavior. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted user input through shell command arguments, creating a potential attack surface if inputs are not properly sanitized by the underlying script.
- Ingestion points: Shell command templates in
SKILL.md(e.g.,python3 scripts/search.py "<product_type> <industry> <keywords>"). - Boundary markers: None identified to delimit or escape user-supplied strings within the shell commands.
- Capability inventory: Execution of shell commands and writing to the local file system within the
design-system/directory. - Sanitization: No explicit sanitization or validation of user-provided keywords is mentioned before they are interpolated into shell commands.
Audit Metadata