multi-brain-debate
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious patterns detected. The skill consists entirely of Markdown and YAML files used to guide the LLM's reasoning process through persona-based simulation.- [NO_CODE] (SAFE): The skill does not include any Python scripts, Node.js code, or shell commands. It operates purely at the prompt level.- [DATA_EXFILTRATION] (SAFE): No network capabilities or file access tools are defined. There is no mechanism to read sensitive data or transmit information externally.- [PROMPT_INJECTION] (SAFE): The instructions define a specific workflow for debate but do not attempt to bypass safety filters or override system-level instructions.- [EXTERNAL_DOWNLOADS] (SAFE): No external dependencies or remote script downloads are referenced in the configuration.
Audit Metadata