initial-access

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains explicit plaintext passwords and examples that embed credentials directly in commands (e.g., --password 'Company2026!') and instructs credential stuffing/copying, which requires handling secret values verbatim and is high risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This content is explicitly malicious: it provides operational, step‑by‑step instructions and tooling to achieve unauthorized initial access (phishing, HTML smuggling with base64‑encoded payloads, ISO/IMG MOTW bypass and DLL sideloading, credential stuffing, exposed‑service exploitation, and supply‑chain compromise), and it details staging, persistence and OPSEC for deploying implants/C2 — facilitating data exfiltration, backdoors/remote code execution, credential theft, system compromise, and supply‑chain attacks.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using public, untrusted web sources and tools (e.g., "Use breach databases to test against target services" and commands like "searchsploit" and "nuclei -u https://vpn.target.com" in the Exposed Service / Credential Stuffing sections), which requires ingesting and interpreting third-party web/forum data that can materially influence subsequent attack decisions and tool use.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt contains explicit, actionable instructions to create and deploy malicious payloads and persistence (e.g., writing DLLs/ISOs, modifying registry and scheduled tasks, deploying C2) which would modify the machine's state if the agent executed them.