Cisco recently released DefenseClaw in response to risks associated with OpenClaw. Here is their write up on this:
AI agents are powerful. Unchecked, they’re dangerous.
Large language model agents — like those built on OpenClaw — can install skills, call MCP servers, execute code, and reach the network. Every one of those actions is an attack surface. A single malicious skill can exfiltrate data. A compromised MCP server can inject hidden instructions. Generated code can contain hardcoded secrets or command injection.
DefenseClaw is the enterprise governance layer for OpenClaw. It sits between your AI agents and the infrastructure they run on, enforcing a simple principle: nothing runs until it’s scanned, and anything dangerous is blocked automatically.
Learn more and check it out HERE.