manage-personas
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a deterministic resolution process by parsing local metadata. It uses regular expressions to extract specific fields from markdown files and does not evaluate or execute untrusted content as code.
- [COMMAND_EXECUTION]: Although executed as a script, the Python code uses only standard library functions and defined internal framework modules. It does not invoke subprocesses or external shell commands.
- [DATA_EXFILTRATION]: The skill does not perform any network operations. It reads local files within the workspace and returns structured data to the agent without external transmission.
- [REMOTE_CODE_EXECUTION]: No remote download or dynamic execution patterns were found. All dependencies are local shared modules, and no untrusted inputs are passed to execution sinks like eval or exec.
Audit Metadata