CVE-2026-33233

AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries

State
Published
Severity
7.6 High
Published
May 19, 2026
Updated
May 19, 2026
Reserved
Mar 18, 2026

Read the record on cve.org

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.

Scores

CVSSScoreVectorSource
3.17.6 HighCVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:HGitHub_M

Weaknesses

  • CWE-502 Deserialization of Untrusted Data
  • CWE-345 Insufficient Verification of Data Authenticity
  • CWE-94 Improper Control of Generation of Code ('Code Injection')

Affected Products

ProductVersions
AutoGPTSignificant-Gravitas
  • >= 0.6.34, < 0.6.52Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.