Vulnerability · Published Jun 24, 2026 · Assigned by GitHub_M
CVE-2026-33235AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features
High 7.7
In plain English
A high-severity uncontrolled resource consumption in AutoGPT from Significant-Gravitas. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 32% of all known vulnerabilities).
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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| Significant-Gravitas | AutoGPT | >= 0.1.0, < 0.6.52 |
Weakness: CWE-400 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H