CWE-87Weakness · CWE-87

CVE-2026-55237

HIGH · 8.8 CVSS v3.1 Published 2026-06-18
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
95/100
Remediation priority · Urgent
Remotely reachable No privileges

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

AutoGPT versions prior to 0.6.62 have a DOM-based XSS vulnerability in the signup page where the `next` URL parameter is improperly validated before being passed to `router.push`, allowing an attacker to craft malicious links that execute arbitrary JavaScript in authenticated users' browsers.

MitigationUpgrade to AutoGPT version 0.6.62 or later which patches the improper validation of the `next` URL parameter.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
Required
Scope
Changed
Confidentiality
High
Integrity
Low
Availability
Low

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:L/A:L

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Determine installed AutoGPT version
    Check the package.json file in the AutoGPT installation directory, or access the application's about/version page if available via the UI or API
    Affected if The version is lower than 0.6.62 (e.g., 0.6.60, 0.6.0, etc.)
  2. Verify signup page is accessible
    Navigate to the signup endpoint of the AutoGPT web interface, typically at /signup or a similar route
    Affected if The signup page loads and accepts a `next` URL parameter in the query string
  3. Inspect the router.push usage for the next parameter
    Examine the frontend source code (likely in a React/Next.js component) handling the signup page, specifically look for code that reads a `next` query parameter and passes it to router.push without validation
    Affected if The code directly uses the `next` parameter value in router.push without sanitization or validation against allowed domains
  4. Test for DOM-based XSS via the next parameter
    Access the signup page with a crafted next parameter such as ?next=javascript:alert(document.domain) and observe if the browser executes the injected JavaScript
    Affected if The injected JavaScript executes in the browser context after form submission or navigation

You are affected if AutoGPT is installed with a version lower than 0.6.62 and the signup page is accessible with an unvalidated `next` parameter that gets used in router.push without proper validation.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade to AutoGPT version 0.6.62 or later which patches the improper validation of the `next` URL parameter.

Recommended fix Moderate confidence

0.6.62

  1. Upgrade AutoGPT to version 0.6.62 or later to address the DOM-based XSS vulnerability
  2. Verify the upgrade was successful by checking the installed version
  3. Test the signup page with the `next` parameter to confirm the vulnerability is remediated (the parameter should now be properly sanitized before being passed to router.push)
  4. Review application logs for any signs of exploitation attempts prior to patching

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation1.0 h
  • Implementation2.0 h
  • Testing2.0 h
  • Review / QA1.0 h
6.0 hours of engineering $1,040
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $1,664.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-55237 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-55237 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data