CVE-2025-41023 Authentication bypass in AutoGPT de Thesamur

Medium 6.9 Published Updated

Attackers can bypass authentication in Thesamur's AutoGPT to access all features without credentials, requiring immediate attention from users.

Exploited in the wild
Not known
Login needed
Not needed
Attackable
Over the internet
Victim action needed
Not needed
Fix
None listed

What is CVE-2025-41023?

CVE-2025-41023 is a medium-severity authentication bypass vulnerability in Thesamur AutoGPT, published on 19 Feb 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

Official description

An authentication bypass vulnerability has been found in Thesamur's AutoGPT. This vulnerability allows an attacker to bypass authentication mechanisms. Once inside the web application, the attacker can use any of its features regardless of the authorisation method used.

Weakness: CWE-287

Which versions are affected by CVE-2025-41023?

How do I fix CVE-2025-41023?

No fix has been published for CVE-2025-41023 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-2025-41023 being exploited?

There is no known exploitation of CVE-2025-41023 in the wild and no public exploit code.

Sources

Also known as GHSA-wmwp-mm98-6v2w.

Is CVE-2025-41023 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free