CVE-2026-33235: AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features
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 Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
AutoGPTto a version that resolves this vulnerability.Fixed in 0.6.52
Event History
Frequently Asked Questions
What is the severity of CVE-2026-33235?
The severity of CVE-2026-33235 is high with a CVSS score of 7.7.
What type of vulnerability is CVE-2026-33235?
CVE-2026-33235 is a Denial of Service (DoS) vulnerability caused by resource exhaustion in the Fill Text Template feature.
How do I fix CVE-2026-33235?
To mitigate CVE-2026-33235, update AutoGPT to version 0.6.52 or later.
Who is affected by CVE-2026-33235?
Versions of AutoGPT prior to 0.6.52 are affected by CVE-2026-33235.
What is the impact of CVE-2026-33235?
The impact of CVE-2026-33235 is a potential Denial of Service that can disrupt the functionality of AutoGPT.