On the 2nd of the month, the AI Security Lab of Ant Group collaborated with Tsinghua University to jointly open-source ClawAegis—a security defense plugin that covers the entire lifecycle of OpenClaw. It aims to systematically address the security and reliability risks faced by OpenClaw, providing autonomous intelligent agents with multi-dimensional, lightweight, and immediate intervention-native protection capabilities.

With the rapid adoption of open-source agent frameworks like OpenClaw, the security risks lurking behind their automation capabilities have become increasingly apparent. From skill poisoning and memory data contamination to malicious intent manipulation, execution of high-risk operations, and even resource exhaustion, agents face challenges throughout their entire lifecycle—from initialization and user input to model inference, intelligent decision-making, and service execution.