ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local script (
search.py) to query design patterns and generate system recommendations. This is the core functional component for its design intelligence features. - [PRIVILEGE_ESCALATION]: Documentation provides standard instructions for environment setup, including the use of "sudo apt install python3" on Linux systems. This is intended for manual execution to prepare the runtime environment and is a standard administrative task.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from local files (such as "ui-reasoning.csv") and user-provided queries to generate UI recommendations. It has the capability to write files to the project directory and execute scripts, which presents an attack surface for instructions embedded in processed data.
- Ingestion points: Data files referenced in the data directory, such as "ui-reasoning.csv" (SKILL.md).
- Boundary markers: None explicitly defined in the instructions for the generated content.
- Capability inventory: Local file writing via the "--persist" flag and subprocess execution of the search script (SKILL.md).
- Sanitization: Not detailed in the instruction file.
Audit Metadata