cheatengine-mcp-automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill instructs the agent to read arbitrary process memory and return values (e.g., read_string, read_bytes, dissect_structure), which can require outputting sensitive secrets (passwords, API keys, tokens) verbatim, creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill explicitly enables arbitrary code execution in other processes (DLL injection, shellcode execution, memory allocation), kernel-level/DBVM ring -1 control, and optional remote shell commands via the MCP bridge—capabilities that directly enable backdoors, RCE, stealthy persistence, and sensitive memory/data theft if abused.

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 enables arbitrary code execution and privileged operations (DLL injection, executing shellcode, allocating memory in other processes, installing DBVM/hypervisor requiring reboot and elevated privileges, and an env var to allow shell commands), which push an agent to change and potentially compromise the host system state.