Mend.io Vulnerability Database
The largest open source vulnerability database
What is a Vulnerability ID?
New vulnerability? Tell us about it!
CVE-2026-33233
Published:May 19, 2026
Updated:June 11, 2026
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.
Affected Packages
https://github.com/Significant-Gravitas/AutoGPT.git (GITHUB):
Affected version(s) >=autogpt-platform-beta-v0.6.34 <autogpt-platform-beta-v0.6.52
Fix Suggestion:
Update to version autogpt-platform-beta-v0.6.52
Do you need more information?
Contact Us
CVSS v4
Base Score:
8.8
Attack Vector
ADJACENT
Attack Complexity
HIGH
Attack Requirements
NONE
Privileges Required
HIGH
User Interaction
NONE
Vulnerable System Confidentiality
HIGH
Vulnerable System Integrity
HIGH
Vulnerable System Availability
HIGH
Subsequent System Confidentiality
HIGH
Subsequent System Integrity
HIGH
Subsequent System Availability
HIGH
CVSS v3
Base Score:
7.6
Attack Vector
ADJACENT
Attack Complexity
HIGH
Privileges Required
HIGH
User Interaction
NONE
Scope
CHANGED
Confidentiality
HIGH
Integrity
HIGH
Availability
HIGH
Weakness Type (CWE)
Deserialization of Untrusted Data
Improper Control of Generation of Code ('Code Injection')
Insufficient Verification of Data Authenticity
EPSS
Base Score:
0.02