privilege-escalation-methods

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill contains many example commands that embed plaintext passwords, NTLM hashes, and explicit credential parameters (and promises "extracted credentials and hashes"), which requires the LLM to handle and potentially output secret values verbatim, posing an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). Direct HTTP link to a PowerShell script on an untrusted "attacker" host is a high-risk distribution vector for malware (direct executable/script from an unknown domain); https://facebook.com is benign.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document is an explicit offensive playbook for privilege escalation, credential harvesting, persistence, and remote code execution—clearly enabling malicious post‑compromise activity.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs the agent to perform privilege escalation and persistent/privileged modifications (sudo exploitation, chmod +s, creating scheduled tasks that add admin users, dumping credential stores, etc.), which directly compromise the host/system state.