prompt-hacking

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content provides explicit, actionable prompt-injection techniques, templates, and code to coerce LLMs into revealing system prompts/credentials and exfiltrating data (direct, indirect, multi-turn, and context-window attacks), and therefore constitutes high-risk malicious guidance enabling data exfiltration and model compromise.