CVE-2025-32423 AutoGPT: There is a DoS vulnerability in ExtractTextInformationBlock
Attackers can cause denial of service in AutoGPT by amplifying input to exhaust server memory resources.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2025-32423?
CVE-2025-32423 is a medium-severity denial of service vulnerability in Significant-Gravitas AutoGPT, published on 26 Jun 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.32, there is a DoS vulnerability in ExtractTextInformationBlock. Malicious users can amplify their input. For example, if a malicious user inputs 10K of content, the server will consume 50G of memory, eventually causing memory resources to be exhausted, resulting in DoS. This vulnerability is fixed in 0.6.32.
Weakness: CWE-770
Which versions are affected by CVE-2025-32423?
How do I fix CVE-2025-32423?
No fix has been published for CVE-2025-32423 yet. Limit exposure of the affected software until one is available.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2025-32423 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-32423 exists.
Sources
Also known as GHSA-pppq-xx2w-7jpq.