enterprise-code-architect
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (INFO): The skill utilizes the 'Read' tool to access local reference files within its own directory. While this is a data ingestion surface, it is used only for static internal documentation and does not process untrusted external content.
- [Data Exposure] (SAFE): No access to sensitive system paths, environmental variables, or hardcoded credentials was found.
- [Command Execution] (SAFE): The skill instructions are limited to read operations and do not attempt to execute shell commands, scripts, or subprocesses.
Audit Metadata