ui-ux-pro-max
Fail
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains instructions to execute high-risk commands with administrative privileges, specifically using
sudo apt update && sudo apt install python3to set up the environment. - [COMMAND_EXECUTION]: The skill's workflow depends on the execution of a local Python script (
skills/ui-ux-pro-max/scripts/search.py) using thepython3command. - [EXTERNAL_DOWNLOADS]: The skill triggers the download and installation of external software (Python 3) from official system repositories through package managers like APT, Homebrew, and Winget.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by passing unvalidated user inputs (product types, keywords, industries) directly as arguments to a command-line interface tool.
- Ingestion points: User-provided query strings in the search.py command (SKILL.md)
- Boundary markers: None present in the instructions
- Capability inventory: Execution of local scripts and file system write operations (SKILL.md)
- Sanitization: No input validation or sanitization is mentioned or performed before passing variables to the subprocess call
Recommendations
- AI detected serious security threats
Audit Metadata