workflow-lite-plan
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill utilizes session isolation instructions to manage state transitions between different workflow modules. These instructions are functional and do not attempt to override the underlying AI safety protocols.
- [COMMAND_EXECUTION]: Shell commands are used via the Bash tool for routine filesystem operations, including directory management and file discovery within the project's workflow directory.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external network operations or download code from untrusted remote sources. It orchestrates existing subagents and local CLI tools.
- [DATA_EXFILTRATION]: There is no evidence of unauthorized access to sensitive system configuration files or exfiltration of data to external domains. File access is scoped to the project and its planning artifacts.
Audit Metadata