ui-ux-pro-max
Warn
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: MEDIUMPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The setup documentation in
SKILL.mdinstructs the user to usesudo apt update && sudo apt install python3to install prerequisites. This involves acquiring administrative privileges to modify system packages. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via command-line arguments to generate UI design systems and code, creating a vulnerability to indirect prompt injection.
- Ingestion points: The user query provided to the
search.pyscript as seen inSKILL.md(e.g.,python3 skills/ui-ux-pro-max/scripts/search.py "<query>"). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the user query as data only and ignore any embedded instructions.
- Capability inventory: The skill can execute shell commands (
python3) and write files to the local filesystem (design-system/directory). - Sanitization: No sanitization, validation, or escaping of the user-provided query is performed before it is passed to the script.
- [COMMAND_EXECUTION]: The skill's primary functionality relies on executing a local Python script (
search.py) usingpython3, where user input is passed as unverified command-line arguments, potentially leading to command injection if the arguments are not correctly handled by the shell environment.
Audit Metadata