ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to execute a bundled Python script (
scripts/search.py) for processing UI/UX queries and managing design data. - [PERSISTENCE]: The skill includes a feature to save design systems to the local filesystem. The
persist_design_systemfunction inscripts/search.pycreates adesign-system/directory and writes markdown files to store project state across multiple interactions. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled inputs (such as industry keywords and page names) which are passed as command-line arguments to a local script that performs file operations.
- Ingestion points: The
queryand--pagearguments inSKILL.mdare derived from user requests and passed toscripts/search.py. - Boundary markers: None present; user input is interpolated directly into shell commands.
- Capability inventory: The script has the capability to write files (
Path.write_text) and create directories within the local workspace. - Sanitization: The script lacks sanitization for the
pageargument. This creates a potential path traversal vulnerability where a specially crafted page name (e.g., using../sequences) could allow the agent to write markdown files outside the intendeddesign-systemdirectory.
Audit Metadata