The open-source AI agent OpenClaw, widely referred to as the "Lobster," has recently seen a surge in popularity. However, experts from the China Academy of Information and Communications Technology (CAICT) have issued a cautionary note, highlighting that despite updates aimed at addressing known vulnerabilities, the system still harbors security risks. Earlier, a platform affiliated with the Ministry of Industry and Information Technology (MIIT) had also raised a security alert, pointing out that OpenClaw, when left in its default settings or improperly configured, could potentially expose users to cyber threats and information breaches. This susceptibility stems from its inherent traits, such as unclear trust boundaries and autonomous decision-making capabilities. In light of these concerns, experts urge users to proceed with caution and adopt robust security practices, including restricting unnecessary public network access and strengthening identity verification mechanisms.