ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing Python through well-known and trusted package managers such as Homebrew (macOS), APT (Linux), and Winget (Windows).
- [COMMAND_EXECUTION]: To install prerequisites on Linux systems, the skill instructs the use of 'sudo' ('sudo apt install python3'), which executes commands with administrative privileges.
- [COMMAND_EXECUTION]: The skill's primary workflow involves executing a local Python script ('search.py') to query UI/UX design information from a shared directory.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes output from an external search tool without implementing sanitization or utilizing explicit boundary markers to isolate the results from instructions.
- Ingestion points: Output returned from the 'search.py' script execution.
- Boundary markers: Absent; search results are processed directly by the agent without delimiters.
- Capability inventory: The agent possesses native tools for file modification and plan updates.
- Sanitization: Absent; search results are not validated or escaped before being incorporated into the agent's workflow.
Audit Metadata