CVE-2026-33235 AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features
Attackers can cause service outages in AutoGPT by submitting computationally expensive Jinja2 expressions that exhaust server 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-2026-33235?
CVE-2026-33235 is a high-severity denial of service vulnerability in Significant-Gravitas AutoGPT, published on 24 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. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and "noisy neighbor" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.
Weakness: CWE-400
Which versions are affected by CVE-2026-33235?
How do I fix CVE-2026-33235?
No fix has been published for CVE-2026-33235 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-2026-33235 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-33235 exists.
Sources
Also known as GHSA-ppw9-h7rv-gwq9.