cheatengine-mcp-automation

SUSPICIOUS. The skill is internally consistent with its stated purpose, but that purpose is to give an AI agent high-impact reverse-engineering and code-injection capabilities against local processes. Installation trust is fairly ordinary aside from unpinned PyPI deps, but the execution scope is broad: memory access, breakpoints, DBVM, DLL injection, shellcode execution, and an optional shell-enabling flag. I see no clear credential harvesting or third-party exfiltration path, so this is not confirmed malware; it is a high-risk offensive automation skill.