onboard-codebase
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard shell commands (
mkdir,git,find) to initialize a workspace within the project directory and list project files. These operations are restricted to the local project root and are standard for codebase analysis tools. - [DATA_EXFILTRATION]: No network operations or external data transmissions were detected. The skill operates entirely on local project data and does not access sensitive user directories like SSH configurations or global environment files.
- [PROMPT_INJECTION]: The instructions do not contain any attempts to bypass safety filters, override system prompts, or manipulate the agent's core behavior.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute code from external sources. It relies on local file analysis and built-in agent capabilities.
Audit Metadata