CVE-2026-33235: DoS (CVSS 7.7)

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.

Is your site exposed to CVE-2026-33235?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

7.7

HIGH

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H

EPSS — Exploit Prediction

0.0031

Probability of exploitation

0.23%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-400 Uncontrolled Resource Consumption

References

Other References

https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52 https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-ppw9-h7rv-gwq9 https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-ppw9-h7rv-gwq9

Frequently Asked Questions

What is CVE-2026-33235? +

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. It has a CVSS v3.1 base score of 7.7 (HIGH).

How severe is CVE-2026-33235? +

CVE-2026-33235 has a CVSS v3.1 score of 7.7 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0031, placing it in the 0th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-33235? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2026-114426

SEPPmail Secure Email Gateway before 15.1.1 processes and writes v1 file-interface upload data before authenticating the caller and without an …

CVE-2026-45802

FPDI is a collection of PHP classes that facilitate reading pages from existing PDF documents and using them as templates …

CVE-2026-67318

axios versions >=1.13.0 (Node.js HTTP adapter) fail to enforce the configured maxBodyLength limit on streamed request bodies when requests are …

CVE-2026-42343

FastGPT is an AI Agent building platform. In versions 4.14.13 and prior, the code-sandbox component suffers from insufficient resource isolation …

CVE-2026-67226

RabbitMQ is a messaging and streaming broker. From 4.0.0 until 4.0.22 and 4.1.14 and 4.2.7, Admin-only atom exhaustion: PUT /api/users …

CVE-2025-41361

Uncontrolled resource consumption vulnerability in IDF v0.10.0-0C03-03 and ZLF v0.10.0-0C03-04. The devices improperly handle TLS requests associated with PROCOME sockets, …