ui-ux-pro-max
Warn
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of an external NPM package
uipro-cliand various system-level packages (python3,brew,apt,winget) through its documentation and templates. - [COMMAND_EXECUTION]: The script
scripts/design_system.pyconstructs filesystem paths for data persistence using user-provided project names without sufficient sanitization. Theproject_sluglogic inpersist_design_systemallows for path traversal (e.g., using..in a project name), which could enable the agent to create directories and write files in unintended locations outside the skill's data directory. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. It ingests untrusted user input to search localized CSV data and then presents the results to the agent without explicit boundary markers or instructions to ignore embedded commands. This could lead to the agent following malicious instructions if the underlying data sources or user queries are manipulated.
Audit Metadata