CVE-2026-33233

What it is

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.6.34 through 0.6.51, the backend deserializes Redis cache bytes using pickle.loads without integrity/authenticity checks. The write path serializes values with pickle.dumps(...) into Redis and the read path blindly invokes pickle.loads(...) on bytes with no HMAC/signature or strict schema validation gating deserialization. If an attacker can poison a shared-cache key in Redis, arbitrary command execution is possible in the backend container context, affecting confidentiality, integrity, and availability. This issue has been fixed in version 0.6.52.

At a glance

Exploitability

Can be exploited from the same network segment with an admin-level account. High risk of data exposure, data tampering, service disruption.

Exploit odds

0.2% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-05-19 02:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-07-24 13:10 UTC Last updatedMost recent change to the record

Details

Published

2026-05-19 02:16 UTC

Last modified

2026-07-24 13:10 UTC

Exploit probability

0.2% · EPSS, next 30 days

Weakness

CWE-94 · Code injection

Record status

Deferred

Attack profile CVSS 3.1 · 7.6

Attack vector

Adjacent network

Complexity

High

Privileges needed

High

User interaction

None

Scope

Changed

Confidentiality

High

Integrity

High

Availability

High