OpenClaw: Hook-triggered CLI runs could receive owner MCP tool authority

Summary OpenClaw hook ingress can start automated agent runs using a configured hook token. In affected releases, a hook-triggered run could select a bundled CLI backend that received owner-scoped MCP loopback authority instead of a scope appropriate for hook ingress. This issue affects the...

CVE-2026-41384 OpenClaw < 2026.3.24 - Environment Variable Injection via Workspace Config in CLI Backend

OpenClaw before 2026.3.24 contains an environment variable injection vulnerability in the CLI backend runner that allows attackers to inject malicious environment variables through workspace configuration. Attackers can craft malicious workspace configs to inject arbitrary environment variables...

CVE-2026-41384: External Control of System or Configuration Setting

OpenClaw before 2026.3.24 contains an environment variable injection vulnerability in the CLI backend runner that allows attackers to inject malicious environment variables through workspace configuration. Attackers can craft malicious workspace configs to inject arbitrary environment variables...

OpenClaw 安全漏洞

OpenClaw is an open-source intelligent artificial assistant developed by OpenClaw. Versions of OpenClaw prior to 2026.3.24 contained security vulnerabilities. These vulnerabilities stemmed from an environment variable injection vulnerability in the CLI backend runner, allowing attackers to inject...

PT-2026-35611

Severity High bg can be injected into shell command construction, leading to possible RCE in affected configurations. Summary elFinder contains a command injection vulnerability in the resize command. The bg background color parameter is accepted from user input and passed through image...