expression-language-injection

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive playbook that provides step‑by‑step RCE payloads, sandbox bypasses, actuator abuse, and exfiltration techniques intended for exploitation and stealth — clearly malicious.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This playbook contains explicit, actionable payloads that invoke Runtime.exec/ProcessBuilder and HTTP actuator actions to add/refresh/delete routes and clear sandbox protections, which enable remote/local RCE and modification of application/system state.