Vulnerability 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.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-be
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37
FAQ
What is CVE-2026-33233?
CVE-2026-33233 is a vulnerability with a CVSS score of 7.6 (HIGH). 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...
How severe is CVE-2026-33233?
CVE-2026-33233 has been rated HIGH with a CVSS base score of 7.6/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-33233?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.