privesc-windows

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is explicitly an offensive post-exploitation/privesc playbook (privilege escalation, UAC bypass, service/registry exploits, credential harvesting with Mimikatz/DCSync, token impersonation, scheduled-task/backdoor persistence, reverse shells and AD abuse) and therefore demonstrates deliberate malicious behavior and backdoor/payload techniques.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill contains explicit, actionable instructions to obtain elevated privileges and directly modify the host state (registry edits, service binary replacement/configuration, scheduled tasks, token impersonation, credential dumping, etc.), which would compromise the machine the agent runs on.