CVE-2026-33235 Details
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.
A denial-of-service vulnerability has been identified in AutoGPT versions prior to 0.6.52, specifically within the Fill Text Template block. The issue arises because, although the backend uses a SandboxedEnvironment to restrict unauthorized access to certain Python attributes, it does not control the computational complexity or execution duration of the expressions processed. This oversight allows attackers to submit resource-intensive Python or Jinja2 expressions that can exhaust the server's CPU and memory, causing the system to hang or crash. In multi-tenant or self-hosted environments, this leads to a complete service disruption, creating 'noisy neighbor' effects that require manual intervention to resolve.
Users can update to AutoGPT version 0.6.52, which addresses this vulnerability by implementing necessary resource governance. Instructions for updating are available on the AutoGPT Releases page.
Metrics
CVSS 4.0 Severity and Vector Strings:
VolerionCVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
Volerion
Assessed Jun 24, 2026CISA-ADP
Assessed Jun 25, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-ppw9-h7rv-gwq9 | CISA-ADP | AdvisoryExploitRemedyVendor |
| https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52 | [email protected] | Release NotesVendor |
| https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-ppw9-h7rv-gwq9 | [email protected] | AdvisoryExploitRemedyVendor |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-400 | Uncontrolled Resource Consumption | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| Significant-Gravitas AutoGPT | >= 0.1.0, < 0.6.52 (semver) |
CPE
Remediation
| |
Change History
2 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Jun 25, 2026 | CVE Modified | CISA-ADP |
| Jun 24, 2026 | New CVE Received | [email protected] |