llm-jailbreaking

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The content is highly malicious: it explicitly instructs advanced LLM jailbreaking and safety-bypass techniques (including base64/zero-width obfuscation, encoded "decode and execute" payloads, fragmentation and multi-vector strategies, and evasion tactics) that enable circumvention of protections and could facilitate data exfiltration, remote exploitation, or other harmful misuse.