behavioral-modes
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No security issues detected. The skill is a collection of instructions for AI response styles.\n- [PROMPT_INJECTION] (SAFE): Persona constraints are legitimate. The use of strong instructional language like 'CRITICAL' or 'NO' is limited to defining output style (e.g., 'NO unnecessary comments') and does not attempt to bypass safety guardrails.\n- [DATA_EXFILTRATION] (SAFE): The skill does not utilize tools for network communication or data movement.\n- [NO_CODE] (SAFE): The skill is composed of natural language instructions in Markdown and does not include any scripts, libraries, or configuration files.
Audit Metadata