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.

Published: 2026-05-19 Last update: 2026-05-19 Assigner: [email protected] Source: [email protected]

Conclusion & alert: CVE-2026-33233 is rated Low Risk (31/100): CVSS High severity, with low exploitation likelihood (EPSS 0.01%). Mandatory action: Monitor for updates and reassess as exploit intelligence or EPSS changes.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Exploit prediction scoring system (EPSS) score for CVE-2026-33233

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-05-19 0.01%

Full EPSS history (1 record total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-33233

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
7.6 3.1 HIGH
CVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H Click to expand
Attack vector (AV:A)
Attacker has to be nearby on the network—same office, same link, that vibe—not the whole wide internet.
Attack complexity (AC:H)
Even with access, the exploit needs extra luck, timing, or a fussy environment to actually work.
Privileges required (PR:H)
They need powerful rights—admin, root, or similar—before this pays off.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:C)
Breaking this can reach past the original component and bite other resources—bigger blast radius.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
1.0 6.0 [email protected]

Weakness enumeration for CVE-2026-33233

Affected software / configurations for CVE-2026-33233

Vendor Product Version Raw CPE
No affected products in dataset.

References for CVE-2026-33233

cvelogic Threat Intelligence