initial-access

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes plaintext passwords and shows a command that passes a password as a command-line argument (e.g., --password 'Company2026!'), which requires the LLM to reproduce secret values verbatim and is a high-risk secret-exfiltration pattern.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document contains explicit, actionable instructions for phishing, payload delivery (HTML smuggling, ISO/IMG, DLL sideloading), credential stuffing, staged implants/C2, and supply-chain compromise—clearly intended to enable unauthorized access, persistence, and data exfiltration.