CVE-2026-33233
HighSummary
AutoGPT versions 0.6.34 through 0.6.51 have a vulnerability that allows deserialization of data from Redis cache without integrity and authenticity checks. An attacker can exploit this vulnerability to execute arbitrary commands in the backend container context.
Risk Assessment
This vulnerability could lead to breaches of confidentiality, integrity, and availability of the system if an attacker manages to poison a shared-cache key in Redis.
Recommendation
It is recommended to upgrade to version 0.6.52, where the issue has been fixed, to secure the system against potential attacks.
Original NVD description (English source)
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.