anti-cheat-systems

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs the agent to fetch and parse untrusted, user-generated content from a public GitHub raw URL (https://raw.githubusercontent.com/gmh5225/awesome-game-security/refs/heads/main/README.md), which the agent would read and interpret as part of its workflow, enabling 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 instructs fetching runtime content from https://raw.githubusercontent.com/gmh5225/awesome-game-security/refs/heads/main/README.md to retrieve and reference sections when answering, so that externally fetched content would directly control prompts/outputs.

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 explicitly teaches and encourages kernel‑level driver loading, driver dumping, DMA/physical memory access, manual mapping and code injection techniques and lists "driver loaders" and other tools that require elevated privileges or bypass security mechanisms, which would compromise the host machine's state.