CVE-2026-33233

high

Description

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.

References

https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9

https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52

Details

Source: Mitre, NVD

Published: 2026-05-19

Updated: 2026-05-19

Risk Information

CVSS v2

Base Score: 6.2

Vector: CVSS2#AV:A/AC:H/Au:M/C:C/I:C/A:C

Severity: Medium

CVSS v3

Base Score: 7.6

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

Severity: High