CVE-2026-33235

HIGHCVSS 7.7/10EPSS 0.31%

Last modified

CVE-2026-33235 is a high-severity vulnerability rated 7.7/10 on the CVSS scale. 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. EPSS estimates a 0.31% chance of exploitation in the next 30 days.

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.

Metrics

CVSS 3.1
7.7/10

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

EPSS Probability
0.31%

22.7th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

References

Timeline

Published
Last Modified
Status
Deferred

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.
How severe is CVE-2026-33235?
CVE-2026-33235 has a CVSS score of 7.7/10 (HIGH severity). The EPSS model estimates a 0.31% probability of exploitation in the next 30 days.
How do I fix CVE-2026-33235?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

Are you affected by CVE-2026-33235?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST