Cyber Resilience

CVE-2026-33233

Deserialization

Published
19 May 2026
Modified
24 July 2026
CVSS Score v3.1 7.6
Click a component to see what it means
Raw vectorCVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H
EPSS Score 0.0023 14th percentile
Risk Priority 51 floored blend · peak EPSS

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 Mark-of-the-Web Bypass (T1553.005); ranked at the 14th 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.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SC-23 (Session Authenticity) — see the control section below for these in your framework.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

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 Techniques

T1553.005 Mark-of-the-Web Bypass Defense Impairment
Adversaries may abuse specific file formats to subvert Mark-of-the-Web (MOTW) controls.
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
T1059.001 PowerShell Execution
Adversaries may abuse PowerShell commands and scripts for execution.
T1059.002 AppleScript Execution
Adversaries may abuse AppleScript for execution.
T1059.004 Unix Shell Execution
Adversaries may abuse Unix shell commands and scripts for execution.
T1059.005 Visual Basic Execution
Adversaries may abuse Visual Basic (VB) for execution.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2023-41898Shared CWE-345, CWE-94
CVE-2024-23601Shared CWE-345, CWE-94
CVE-2026-67531Shared CWE-94
CVE-2025-61929Shared CWE-94
CVE-2025-67509Shared CWE-94
CVE-2025-61260Shared CWE-94
CVE-2026-26030Shared CWE-94
CVE-2026-45555Shared CWE-94
CVE-2025-5120Shared CWE-94
CVE-2026-27597Shared CWE-94

Affected Assets

In
inferred from references and description; NVD did not file a CPE for this CVE

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)
  • 8 hardening rules · 5 OS baselines
Validate
Prove the fix (OWASP ASVS)
  • V3.5.5
  • V1.3.1

Mitigating Controls (NIST 800-53 r5) AI

Explicit requirement to protect session authenticity structurally prevents the weakness for communications.

Developer testing and evaluation finds code paths that accept and execute externally influenced strings.

Input validation directly stops untrusted data from being used to construct executable code without neutralization.

Integrity verification tools detect (but do not stop) the acceptance of data lacking authenticity.

Least privilege limits the damage an injected code fragment can perform once executed.

Requiring documented secure development standards and tools enforces use of safe code-generation APIs and escaping.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.PS-06 mostly match
prevents

PR.PS-06's SDLC practices directly target injection flaws via secure coding and testing (mostly), yet as a single broad outcome it leaves many code-generation specifics unaddressed (partial).

RC.RP-05 mostly match
degrades

CWE-345 directly impairs RC.RP-05's verification of restored-asset integrity/authenticity, largely defeating the outcome while still leaving other restoration-confirmation steps partially viable.

PR.DS-10 none match
prevents

PR.DS-10 protects runtime data confidentiality/integrity but has no bearing on neutralizing externally influenced input during code generation, so neither direction shows any preventive effect.

PR.PS-02 none match
prevents

PR.PS-02 addresses only post-deployment updates/patching and cannot prevent introduction of unsafe deserialization code, yet it can remediate some instances when the flaw exists in outdated libraries or components.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Security testing can detect missing or weak data authenticity verification.

mitigates

Network controls can enforce authenticated channels, reducing risk of accepting unauthentic data.

mitigates

Secure network services often include authenticity checks for data exchanged over those services.

prevents

Cryptographic mechanisms directly verify data origin and integrity, preventing acceptance of unauthentic data.

prevents

Secure SDLC incorporates authenticity verification requirements throughout development.

prevents

Application security requirements can mandate data authenticity verification mechanisms.

Hardening callouts derived

Configuration rules from DISA STIG baselines that bear on weaknesses of the type cited by this CVE. Each rule is shown with the relationship its mapping actually records, against the CWE it was authored against. Derived via CVE→CWE over `controls_xwalks` (authoritative rows only; rows rated `none` are excluded).

Oracle Linux 8 (2 rules)
  • V-248574 YUM must be configured to prevent the installation of patches, service packs, device drivers, or OL 8 system components that have not been digitally signed using a certificate that is recognized and approved by the organization. prevents CWE-345
  • V-248575 OL 8 must prevent the installation of software, patches, service packs, device drivers, or operating system components of local packages without verification they have been digitally signed using a certificate that is issued by a Certificate Authority (CA) that is recognized and approved by the organization. prevents CWE-345
Oracle Linux 9 (1 rule)
  • V-271525 OL 9 must have GPG signature verification enabled for all software repositories. prevents CWE-345
RHEL 7 (2 rules)
  • V-204447 The Red Hat Enterprise Linux operating system must prevent the installation of software, patches, service packs, device drivers, or operating system components from a repository without verification they have been digitally signed using a certificate that is issued by a Certificate Authority (CA) that is recognized and approved by the organization. prevents CWE-345
  • V-204448 The Red Hat Enterprise Linux operating system must prevent the installation of software, patches, service packs, device drivers, or operating system components of local packages without verification they have been digitally signed using a certificate that is issued by a Certificate Authority (CA) that is recognized and approved by the organization. prevents CWE-345
RHEL 8 (2 rules)
  • V-230264 RHEL 8 must prevent the installation of software, patches, service packs, device drivers, or operating system components from a repository without verification they have been digitally signed using a certificate that is issued by a Certificate Authority (CA) that is recognized and approved by the organization. prevents CWE-345
  • V-230265 RHEL 8 must prevent the installation of software, patches, service packs, device drivers, or operating system components of local packages without verification they have been digitally signed using a certificate that is issued by a Certificate Authority (CA) that is recognized and approved by the organization. prevents CWE-345
RHEL 9 (1 rule)
  • V-257822 RHEL 9 must have GPG signature verification enabled for all software repositories. prevents CWE-345

References