CVE-2026-33233: AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries
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 Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
AutoGPT Platformto a version that resolves this vulnerability.Fixed in 0.6.52
Event History
Frequently Asked Questions
What is the severity of CVE-2026-33233?
CVE-2026-33233 has a high severity level due to its potential for remote code execution.
How do I fix CVE-2026-33233?
To fix CVE-2026-33233, upgrade the AutoGPT Platform to version 0.6.52 or later.
What versions are affected by CVE-2026-33233?
CVE-2026-33233 affects AutoGPT Platform versions from 0.6.34 to 0.6.51.
What type of vulnerability is CVE-2026-33233?
CVE-2026-33233 is a remote code execution vulnerability due to unsafe pickle deserialization.
Who is the vendor for CVE-2026-33233?
The vendor for CVE-2026-33233 is AutoGPT.