execute

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.95). The document contains explicit instructions to operate fully autonomously (never ask the user) and to spawn tasks/agents with a "bypassPermissions" mode to perform work, which deliberately encourages bypassing access controls and performing unauthorized actions—this is a high-risk backdoor/abuse pattern even though there is no direct data-exfiltration or obfuscated payload in the text.