OpenClaw 2026.3.31 is here, and I noticed this is what I'm interested in: Skills/install and Plugins/install: Built-in dangerous-code critical findings and install-time scan failures now fail closed by default, so plugin installs and gateway-backed skill dependency installs that previously succeeded may now require an explicit dangerous override such as `--dangerously-force-unsafe-install` to proceed. In other words, during skill and plugin installation, if high-risk code (critical findings) is detected or the scan fails, the installation will be blocked by default, preventing the forced installation of malicious code as before. I haven't had a chance to verify this yet, but those interested in this upgrade can give it a try. OpenClaw is actively improving its security capabilities, and hopefully its stability and resilience will also improve.

Big head 🤦‍♂️

See, another update is coming soon. Aside from some improvements to the Skill/Plugin security mechanism, the annoying command execution approve mechanism has been removed by default... Ugh, can't we really be more careful with every update?