game-hacking-techniques

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill is explicitly an offensive guide describing memory injection, kernel/hypervisor/DMA access, driver-based privilege escalation, and obfuscation/evasion techniques that enable stealthy unauthorized process manipulation and potential system compromise.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md Data Source section explicitly instructs the agent to fetch and read public raw GitHub URLs (e.g., https://raw.githubusercontent.com/gmh5225/awesome-game-security/... for README, archive, and description files), meaning the agent will ingest and act on untrusted, user-generated third-party content as part of its workflow.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and inject remote content at runtime from raw GitHub URLs (e.g., https://raw.githubusercontent.com/gmh5225/awesome-game-security/refs/heads/main/README.md), which would directly control model context/prompts and is described as a required data source.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill provides detailed, actionable guidance on kernel-mode drivers, DMA/hypervisor memory access, driver-based input and other privileged techniques that enable installing or manipulating kernel components and hardware—actions that modify and can compromise the host machine's state.