CVE-2025-55012 Zed AI Agent Remote Code Execution
An AI agent in the Zed editor could bypass permission checks to execute arbitrary commands on a victim's machine.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- A user has to click or open something
- Fix
- None listed
What is CVE-2025-55012?
CVE-2025-55012 is a high-severity authentication bypass vulnerability in zed-industries zed, published on 11 Aug 2025. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.
Official description
Zed is a multiplayer code editor. Prior to version 0.197.3, in the Zed Agent Panel allowed for an AI agent to achieve Remote Code Execution (RCE) by bypassing user permission checks. An AI Agent could have exploited a permissions bypass vulnerability to create or modify a project-specific configuration file, leading to the execution of arbitrary commands on a victim's machine without the explicit approval that would otherwise be required. This vulnerability has been patched in version 0.197.3. A workaround for this issue involves either avoid sending prompts to the Agent Panel, or to limit the AI Agent's file system access.
Which versions are affected by CVE-2025-55012?
How do I fix CVE-2025-55012?
No fix has been published for CVE-2025-55012 yet. Limit exposure of the affected software until one is available.
Upgrade, and rotate credentials and sessions that may have been exposed. More about Authentication bypass.
Is CVE-2025-55012 being exploited?
There is no known exploitation of CVE-2025-55012 in the wild and no public exploit code.
Sources
Also known as GHSA-x34m-39xw-g2wr.