prompt-jailbreak

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The document is explicitly malicious: it provides detailed, actionable jailbreak and adversarial techniques (role-play bypasses, encoding/obfuscation, prompt injection, system-prompt/JSON/XML overrides, SSRF/agent tool misuse, RCE guidance, data-exfiltration tactics) intended to circumvent LLM safety, steal sensitive data, and enable remote code/tool execution.