game-hacking-techniques

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). High risk: the content explicitly documents process injection, shellcode/manual-mapped DLL loading, kernel-mode drivers (IOCTL/KeStackAttachProcess/Win32k hooks), EFI/hypervisor/DMA-level memory access, overlay hijacking, and obfuscation/anti-detection techniques — all clear enablers for stealthy backdoors, remote code execution, persistence, and system compromise.

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to fetch and reference content from a public GitHub raw URL (https://raw.githubusercontent.com/gmh5225/awesome-game-security/refs/heads/main/README.md), meaning the agent will ingest untrusted, user-generated third‑party content and act on it to answer user queries, which could allow indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly directs the agent at runtime to fetch and reference content from https://raw.githubusercontent.com/gmh5225/awesome-game-security/refs/heads/main/README.md, so external raw GitHub content would be retrieved and injected into the agent's responses, directly controlling prompts and acting as a required dependency.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The skill explicitly describes kernel-mode drivers, driver-based access, syscall/Win32k hooks, registry callbacks, driver communication and other techniques that require installing kernel drivers or modifying OS components and thus push actions that would modify and compromise the host system state and bypass protections.