Is CVE-2026-33233 exploited in the wild?

No. Junglewise Threat Intelligence has no report of CVE-2026-33233 being exploited in the wild.

How severe is CVE-2026-33233?

High severity, with a CVSS score of 7.6, published 19 May 2026.

Which products and versions are affected?

Significant-Gravitas AutoGPT Platform Backend 0.6.34 through 0.6.51.

Is there a fix for CVE-2026-33233?

A patch was published on 2026-03-20: Version 0.6.52 released Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

How is CVE-2026-33233 attacked?

It is attacked from the adjacent network, in a network appliance.

Am I affected by CVE-2026-33233?

Check whether you run Significant-Gravitas AutoGPT Platform Backend at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

CVE-2026-33233: Significant-Gravitas AutoGPT unsafe deserialization in Redis cache

CVE-2026-33233 · Severity: high · CVSS 7.6 · Published 2026-05-19

AutoGPT is an automation platform used to create and manage autonomous AI agents. A security vulnerability in the platform's backend allows for the execution of unauthorized commands if an attacker can manipulate the data stored in the system's Redis cache. This could lead to a total compromise of the backend server, potentially exposing sensitive data or disrupting AI agent operations.

Technologies: Significant-Gravitas AutoGPT Platform Backend. Vendors: Significant-Gravitas.

Quick answers

Is CVE-2026-33233 exploited in the wild?: No. Junglewise Threat Intelligence has no report of CVE-2026-33233 being exploited in the wild.
How severe is CVE-2026-33233?: High severity, with a CVSS score of 7.6, published 19 May 2026.
Which products and versions are affected?: Significant-Gravitas AutoGPT Platform Backend 0.6.34 through 0.6.51.
Is there a fix for CVE-2026-33233?: A patch was published on 2026-03-20: Version 0.6.52 released Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-33233 attacked?: It is attacked from the adjacent network, in a network appliance.
Am I affected by CVE-2026-33233?: Check whether you run Significant-Gravitas AutoGPT Platform Backend at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

Technical details

The AutoGPT Platform backend (specifically in `autogpt_platform/backend/backend/util/cache.py`) utilizes the Python `pickle` module to serialize and deserialize data stored in a Redis cache. The implementation lacks integrity checks, such as HMAC signatures or strict schema validation, when reading from the cache. An attacker who gains the ability to poison Redis cache keys—requiring adjacent network access and high privileges—can inject a malicious pickle payload. Upon deserialization via `pickle.loads()`, this payload triggers arbitrary command execution within the context of the backend container. The issue is addressed in version 0.6.52 by moving away from unsafe deserialization.

Affected products

Significant-Gravitas AutoGPT Platform Backend 0.6.34 through 0.6.51

Timeline

2026-03-20: patched: Version 0.6.52 released
2026-05-11: advisory: GitHub Security Advisory published
2026-05-19: disclosed: CVE published to NVD

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.