privesc-windows

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes commands that require embedding or producing plaintext secrets (e.g., /password:pass, /rc4:HASH and mimikatz dumps), which would force the LLM to handle or output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit post-exploitation playbook: it provides step-by-step commands to gain SYSTEM, create persistent backdoors, perform UAC bypasses, replace service binaries, and harvest and export credentials—clearly intended for malicious privilege escalation and credential theft.

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 explicitly instructs modifying system state (registry changes to bypass UAC, changing service binaries, replacing/writing system files, creating SYSTEM scheduled tasks, installing MSIs, and running credential-stealing/tools like Mimikatz and token exploits) to escalate privileges, which compromises the host machine.