ui-ux-pro-max
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of local Python scripts (
scripts/search.py) to process user queries and retrieve design information from internal CSV files. - [COMMAND_EXECUTION]: The skill's instructions guide the agent to perform environment setup tasks, including checking for Python and installing it via system package managers such as
brew,apt, andwinget(e.g.,sudo apt install python3). - [PROMPT_INJECTION]: The skill features a potential surface for indirect prompt injection (Category 8) by processing user-supplied queries and incorporating the resulting data into the agent's context.
- Ingestion points: Data retrieved from multiple CSV files in the
data/directory via thesearch.pyscript. - Boundary markers: Absent. The results from the search scripts are integrated into the agent's workflow without the use of delimiters or specific instructions to ignore embedded commands.
- Capability inventory: The skill possesses the capability to execute shell commands and Python scripts.
- Sanitization: Absent. The skill performs a BM25 text search and returns the raw contents of matching CSV rows.
Audit Metadata