create-persona
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: No malicious code or dangerous execution patterns were detected in the skill instructions. The functionality is limited to local file system operations within the project directory.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it reads instructions from an external template file. 1. Ingestion points: 'claude_settings/python/templates/persona-template.md'. 2. Boundary markers: Absent in the instructions. 3. Capability inventory: File system read and write. 4. Sanitization: No validation of template content is described.
- [NO_CODE]: The skill contains no executable scripts or code files, relying solely on natural language instructions for the agent's behavior.
Audit Metadata