Clawshell 0.1.0

Multi-layer blocklist guard for OpenClaw. Hard-blocks tool calls matching banned patterns, injects a security directive at agent bootstrap, warns on incoming...

Human-in-the-loop security layer. Intercepts high-risk commands and requires push notification approval.

Evaluates agent actions for security risks, enforcing least-privilege policies with allow, deny, or confirmation decisions and secret redaction.

Runs shell commands exclusively inside tmux session 'claw', captures output, and requests confirmation for potentially destructive commands.

Enterprise-grade security for OpenClaw - blocks malicious skills, detects hallucinated packages, and prevents prompt injection attacks. Powered by agent-secu...

Unified security suite for agent workspaces. Installs, configures, and orchestrates all 11 OpenClaw security tools in one command — integrity, secrets, permissions, network, audit trail, signing, supply chain, credentials, injection defense, compliance, and incident response.