"Four vulnerabilities in the OpenClaw AI assistant can be chained together to plant backdoors on the underlying host, cybersecurity firm Cyera warns. The bugs, collectively known as Claw Chain, allow an attacker with code execution privileges inside the sandbox to control the agent runtime and abuse it to compromise the system. According to Cyera, the attacker can rely on prompt injections, malicious plugins, and compromised external input to trigger the attack chain and turn the AI into their own assistant."
"After gaining code execution within the OpenShell sandbox, the attacker can exploit a race condition (CVE-2026-44113) to read files outside the mount root, or an exec allowlist analysis bug (CVE-2026-44115) to execute unapproved commands at runtime. Successful exploitation of these issues, Cyera notes, allows the attacker to bypass sandbox restrictions and leak credentials, API keys, tokens, configuration files, and other sensitive data."
"Next, the attacker can exploit an MCP loopback flaw (CVE-2026-44118) to manipulate the unverified ownership flag and elevate their privileges to owner-level. The attacker gains access to critical management functions, including configuration and orchestration of execution. Finally, the attacker can exploit the fourth vulnerability, a critical-severity race condition in the OpenShell sandbox (CVE-2026-44112, CVSS score of 9.6), to write data outside the sandbox boundary."
"It allows the attacker to modify configurations, plant backdoors, and gain persistent control of the host. "By weaponizing the agent's own privileges, an adversary moves through data access, privilege escalation, and persistence - using the agent as their hands inside the environment. Each step looks like normal agent behavior to traditional controls, broadening blast radius and making detection significantly harder," Cyera says."
Four OpenClaw AI assistant vulnerabilities can be chained to plant backdoors on the underlying host. An attacker with code execution inside the sandbox can control the agent runtime and abuse it to compromise the system. Prompt injections, malicious plugins, and compromised external input can trigger the chain and turn the AI into an attacker-controlled assistant. After code execution in the OpenShell sandbox, a race condition can read files outside the mount root, and an exec allowlist analysis bug can run unapproved commands. An MCP loopback flaw can manipulate an ownership flag to elevate privileges to owner level and access management functions. A critical race condition can write data outside the sandbox boundary, modify configurations, plant backdoors, and maintain persistent control.
Read at SecurityWeek
Unable to calculate read time
Collection
[
|
...
]