CVE-2026-33233
CVE-2026-33233 is a high-severity vulnerability with a CVSS 3.x base score of 7.6. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-94.
Key facts
- Severity: High (CVSS 3.x base score 7.6)
- EPSS exploit prediction: 0% (14th percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2026-30817
- Weakness: CWE-94
- Published:
- Last modified:
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.
Frequently asked questions
- What is CVE-2026-33233?
- 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.
- How severe is CVE-2026-33233?
- CVE-2026-33233 has a CVSS 3.x base score of 7.6, rated high severity. It is exploitable over an adjacent network with high attack complexity, requires high privileges and no user interaction. Impact on confidentiality is high, integrity high, and availability high.
- Is CVE-2026-33233 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (14th percentile), an estimate of the probability of exploitation in the next 30 days.
- How do I fix CVE-2026-33233?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
- Does CVE-2026-33233 have an EU (EUVD) identifier?
- Yes. CVE-2026-33233 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-30817.
- When was CVE-2026-33233 published?
- CVE-2026-33233 was published on 2026-05-19 and last updated on 2026-06-17.
References
- https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-rfg2-37xq-w4m9
Other CWE-94 (Code Injection) vulnerabilities
- CVE-2026-57624 — Critical (CVSS 10.0): Unauthenticated Remote Code Execution (RCE) in Blocksy Companion Pro <= 2.1.46 versions.
- CVE-2026-10134 — Critical (CVSS 10.0): IBM Langflow OSS 1.0.0 through 1.9.3 allows an attacker to read every secret available to the Langflow process, read…
- CVE-2026-53576 — Critical (CVSS 10.0): Kestra is an open-source, event-driven orchestration platform. Prior to 1.0.45 and 1.3.21, the authentication filter…
- CVE-2026-10561 — Critical (CVSS 10.0): IBM Langflow OSS 1.0.0 through 1.9.3 has an vulnerability due to an improper isolation of Python execution combined…
- CVE-2026-25470 — Critical (CVSS 10.0): Improper Control of Generation of Code ('Code Injection') vulnerability in ACPT ACPT (Pro) - Custom Post Types Plugin…
- CVE-2026-48836 — Critical (CVSS 10.0): Unauthenticated Remote Code Execution (RCE) in Easy Invoice <= 2.1.19 versions.