PT-2026-23555

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.2.14 clawdbot versions prior to 2026.1.24-3 Description The Telegram allowlist authorization mechanism incorrectly matched on mutable usernames @username instead of immutable numeric sender IDs. This allowed...

OpenClaw OS Command Injection Vulnerability

OpenClaw is openclaw open source an intelligent artificial assistant. An operating system command injection vulnerability exists in versions prior to OpenClaw 2026.1.29, which stems from the sshNodeCommand function failing to properly filter construct command special characters, commands, etc. An...

OpenClaw Access Control Error Vulnerability (CNVD-2026-13431)

OpenClaw is openclaw open source an intelligent artificial assistant. OpenClaw suffers from an Access Control Error vulnerability that originates from the fact that an unauthenticated local client can use the Gateway WebSocket API to write a configuration via config.apply and set insecure cliPath...

OpenClaw Information Disclosure Vulnerability

OpenClaw is openclaw open source an intelligent artificial assistant. OpenClaw has an information disclosure vulnerability that stems from the isValidMedia function allowing arbitrary file paths, which can be exploited by an attacker to cause the reading of arbitrary files and the disclosure of...

OpenClaw OS Command Injection Vulnerability (CNVD-2026-13291)

OpenClaw is openclaw open source an intelligent artificial assistant. OpenClaw there is an operating system command injection vulnerability , the vulnerability stems from the Docker sandbox execution mechanism when constructing shell commands on the PATH environment variable handling insecurity ,...

OpenClaw < 2026.1.30 Path Traversal (GHSA-r8g4-86fx-92mq)

The version of the OpenClaw AI assistant installed on the remote host is prior to 2026.1.30. It is, therefore, affected by a path traversal vulnerability: - The isValidMedia function in src/media/parse.ts allows arbitrary file paths including absolute paths, home directory paths, and directory...

OpenClaw < 2026.1.20 Command Injection (GHSA-g55j-c2v4-pjcg)

The version of the OpenClaw AI assistant installed on the remote host is prior to 2026.1.20. It is, therefore, affected by a command injection vulnerability: - An unauthenticated local client could use the Gateway WebSocket API to write config via config.apply and set unsafe cliPath values that...

Command Injection

OpenClaw is vulnerable to Command Injection. The vulnerability is due to unsafe handling of the PATH environment variable when constructing shell commands in the Docker sandbox, which allows an authenticated attacker to influence command execution within the container context...

Your OpenClaw Agent Doesn't Sleep. Your Laptop Does. Move It to the Cloud.

...

Origin Validation Error

Overview openclaw is a 🦞 OpenClaw — Personal AI Assistant Affected versions of this package are vulnerable to Origin Validation Error via the /cdp WebSocket endpoint that accepts arbitrary Chrome DevTools Protocol commands. An attacker can bypass the intended localhost-only restriction by running...

Exploit for CVE-2026-25253

CVE-2026-25253 Proof of Concept One-click RCE on OpenClaw via...

CVE-2026-25593

OpenClaw is a personal AI assistant. Prior to 2026.1.20, an unauthenticated local client could use the Gateway WebSocket API to write config via config.apply and set unsafe cliPath values that were later used for command discovery, enabling command injection as the gateway user. This vulnerabilit...

CVE-2026-25593 OpenClaw Affected by Unauthenticated Local RCE via WebSocket config.apply

OpenClaw is a personal AI assistant. Prior to 2026.1.20, an unauthenticated local client could use the Gateway WebSocket API to write config via config.apply and set unsafe cliPath values that were later used for command discovery, enabling command injection as the gateway user. This vulnerabilit...

CVE-2026-25593 OpenClaw Affected by Unauthenticated Local RCE via WebSocket config.apply

OpenClaw is a personal AI assistant. Prior to 2026.1.20, an unauthenticated local client could use the Gateway WebSocket API to write config via config.apply and set unsafe cliPath values that were later used for command discovery, enabling command injection as the gateway user. This vulnerabilit...

EUVD-2026-5577

OpenClaw is a personal AI assistant. Prior to 2026.1.20, an unauthenticated local client could use the Gateway WebSocket API to write config via config.apply and set unsafe cliPath values that were later used for command discovery, enabling command injection as the gateway user. This vulnerabilit...

CVE-2026-25593 OpenClaw Affected by Unauthenticated Local RCE via WebSocket config.apply

OpenClaw is a personal AI assistant. Prior to 2026.1.20, an unauthenticated local client could use the Gateway WebSocket API to write config via config.apply and set unsafe cliPath values that were later used for command discovery, enabling command injection as the gateway user. This vulnerabilit...

17% of 3rd-Party Add-Ons for OpenClaw Used in Crypto Theft and macOS Malware

Bitdefender Labs reveals that 17% of OpenClaw AI skills analyzed in February 2026 are malicious. With over 160,000…...

CVE-2026-25157

OpenClaw is a personal AI assistant. Prior to version 2026.1.29, there is an OS command injection vulnerability via the Project Root Path in sshNodeCommand. The sshNodeCommand function constructed a shell script without properly escaping the user-supplied project path in an error message. When th...

OpenClaw 访问控制错误漏洞

OpenClaw is openclaw open source an intelligent artificial assistant. OpenClaw suffers from an Access Control Error vulnerability that originates from the fact that an unauthenticated local client can use the Gateway WebSocket API to write a configuration via config.apply and set insecure cliPath...

Viral AI, Invisible Risks: What OpenClaw Reveals About Agentic Assistants

OpenClaw aka Clawdbot or Moltbot represents a new frontier in agentic AI: powerful, highly autonomous, and surprisingly easy to use. In this research, we examine how its capabilities compare to its predecessors’ and highlight the security risks inherent to the agentic AI paradigm...