---
cve: "CVE-2026-33235"
severity: "HIGH"
cvss: 7.7
epss: "0.5%"
vendor: "Significant-Gravitas"
kev: false
exploited: false
published: "2026-06-24 21:16:53"
tags: [cve, security, high]
source: tsecurity.de CVE-Dossier
exported: "2026-09-22T23:20:34+02:00"
---

# CVE-2026-33235

> 7.7 HIGH · 🧪 PoC

## Beschreibung

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.

## CVSS-Vektor

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

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Gering | bad |
| PR Privilegien | Gering | warn |
| UI Interaktion | Keine | bad |
| S Scope | Verändert | bad |
| C Vertraulichkeit | Keine | good |
| I Integrität | Keine | good |
| A Verfügbarkeit | Hoch | bad |

## Patch verfügbar (OSV)

- f01f6686744e1913334641bd2242fc0ed2a1bbc6 (Commit)

## Referenzen

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

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-33235) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_