CVE-2026-33233

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.
Configurations

No configuration.

History

19 May 2026, 15:16

Type Values Removed Values Added
References () https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9 - () https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9 -

19 May 2026, 02:16

Type Values Removed Values Added
New CVE

Information

Published : 2026-05-19 02:16

Updated : 2026-05-19 15:16


NVD link : CVE-2026-33233

Mitre link : CVE-2026-33233

CVE.ORG link : CVE-2026-33233


JSON object : View

Products Affected

No product.

CWE
CWE-94

Improper Control of Generation of Code ('Code Injection')

CWE-345

Insufficient Verification of Data Authenticity

CWE-502

Deserialization of Untrusted Data