Vulnerability · Published May 19, 2026 · Assigned by GitHub_M
CVE-2026-33233AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries
High 7.6
In plain English
A high-severity unsafe deserialization in AutoGPT from Significant-Gravitas. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 14% of all known vulnerabilities).
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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| Significant-Gravitas | AutoGPT | >= 0.6.34, < 0.6.52 |
Weakness: CWE-502, CWE-345, CWE-94 · Vector: CVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H