behavioral-modes
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured framework for AI operational modes and does not contain any malicious code or instructions.
- [DATA_EXFILTRATION]: The skill configuration is restricted to file-reading tools (
Read,Glob,Grep) and lacks network capabilities, ensuring that processed data cannot be sent externally. - [COMMAND_EXECUTION]: No unauthorized shell commands or privilege escalation patterns were detected. The skill instructions focus on communication and code style rather than system-level operations.
- [PROMPT_INJECTION]: The mode-switching triggers (e.g.,
/debug,/brainstorm) and behavioral constraints are part of the intended functional design and do not attempt to override agent safety or system instructions.
Audit Metadata