multi-brain

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill contains no explicit malware or remote-exec code, but it mandates always exposing internal "3 perspectives" and consensus (effectively forcing disclosure of internal reasoning/system prompts) and allows implicit invocation — enabling potential exfiltration of sensitive model-internal data or unauthorized automated activation, which is a high-risk backdoor/data-leak pattern.