malware-game-cheat-detection

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill includes examples and templates that read and then embed secrets verbatim (e.g., archive passwords in reports and placeholders for API keys/GITHUB_TOKEN exported into environment/commands), which would require the LLM to output sensitive values directly and present an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). These URLs are suspicious: a GitHub "trainer" repo points to direct .zip archives hosted on a personal Netlify site (unknown uploader) — direct archive/executable links on third‑party hosting for game cheats are a common malware distribution pattern (often password‑protected or requiring elevated privileges).