CVE-2026-55237 AutoGPT SignUp Page has DOM-Based XSS and Open Redirect
Attackers can execute arbitrary JavaScript or redirect users via a malicious link on the signup page, potentially stealing credentials or performing unauthorized actions.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- A user has to click or open something
- Fix
- None listed
What is CVE-2026-55237?
CVE-2026-55237 is a high-severity cross-site scripting vulnerability in Significant-Gravitas AutoGPT, published on 18 Jun 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Official description
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Versions prior to 0.6.62 have a DOM-based Cross-Site Scripting (XSS) vulnerability in AutoGPT's signup page. The application improperly trusts a URL parameter (`next`), which is passed to `router.push`. An attacker can craft a malicious link that, when opened by an authenticated user, performs a client-side redirect and executes arbitrary JavaScript in the context of their browser. This could lead to credential theft, internal network pivoting, and unauthorized actions performed on behalf of the victim. Version 0.6.62 patches the issue.
Which versions are affected by CVE-2026-55237?
How do I fix CVE-2026-55237?
No fix has been published for CVE-2026-55237 yet. Limit exposure of the affected software until one is available.
Escape output for the context it lands in and set a strict Content Security Policy. Upgrading the affected component is the real fix. More about Cross-site scripting.
Is CVE-2026-55237 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-55237 exists.
Sources
Also known as GHSA-j2cp-jg5q-38wj.