CVE-2026-33233 AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries
Attackers can execute arbitrary code by poisoning Redis cache entries due to unsafe pickle deserialization in the AutoGPT backend.
- Exploited in the wild
- Not known
- Login needed
- An administrator
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-33233?
CVE-2026-33233 is a high-severity unsafe deserialization vulnerability in Significant-Gravitas AutoGPT, published on 19 May 2026. It can only be exploited from the same machine or local network, with no action from the victim.
Official 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.
Which versions are affected by CVE-2026-33233?
How do I fix CVE-2026-33233?
No fix has been published for CVE-2026-33233 yet. Limit exposure of the affected software until one is available.
Upgrade, and only deserialise data from trusted sources or with an allow-list of types. More about Unsafe deserialization.
Is CVE-2026-33233 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-33233 exists.
Sources
Also known as GHSA-rfg2-37xq-w4m9.