personas
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security vulnerabilities, malicious patterns, or obfuscation were detected. The skill operates as a collection of static instructions and personality definitions.
- [NO_CODE]: The skill does not provide any executable scripts (e.g., Python, JavaScript, Shell). It relies entirely on the host agent's ability to interpret markdown-based prompts and perform basic file operations.
- [COMMAND_EXECUTION]: The skill defines a workflow for the agent to read and write persona definitions in a local 'data' directory. This functionality is restricted to the skill's own file structure and is used solely for persona management, posing no risk of arbitrary system command execution.
- [PROMPT_INJECTION]: Although the skill is designed to influence agent behavior through personas, it includes clear boundary instructions and disclaimers. It specifically mandates that medical, legal, and financial personas must not provide professional advice and should redirect users to licensed professionals.
Audit Metadata