CVE-2026-33233
Published: 19 May 2026
Summary
CVE-2026-33233 is a high-severity Code Injection (CWE-94) vulnerability. Its CVSS base score is 7.6 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Python (T1059.006); ranked at the 13.5th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Supply Chain and Deployment risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-30817
Vulnerability details
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: artificial intelligence, autogpt
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Insecure pickle deserialization (CWE-502) of untrusted Redis cache data directly enables arbitrary Python code execution in the backend process.
CVEs Like This One
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Untrusted serialized data can be deserialized and observed inside the chamber, blocking gadget-chain exploitation outside the sandbox.
Validates inputs used in dynamic code generation to block injected directives.
Mandates verification of data authenticity for software, firmware, and information.
Provenance documentation and monitoring directly enables verification of authenticity for components and data throughout their history.
Penetration testing supplies malicious serialized objects, detecting unsafe deserialization and supporting corrective actions.
Directly requires independent verification of matching output before adverse decisions, mitigating insufficient authenticity checks on data from external sources.
Evaluation of untrusted data handling (deserialization testing) reveals unsafe processing, which the required remediation process addresses.
Use of approved PKI certificates provides verifiable data authenticity and origin for communications and artifacts.