Cyber Resilience

CVE-2026-41523

RCE in Vllm ≤ 0.22.0

Public PoCRCE
Published
22 June 2026
Modified
15 July 2026
Patch / advisory
CVSS Score v3.1 7.5
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
EPSS Score 0.0075 52th percentile
Risk Priority 57 floored blend · peak EPSS

Summary

CVE-2026-41523 is a high-severity Code Injection (CWE-94) vulnerability in Vllm Vllm. Its CVSS base score is 7.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Application or System Exploitation (T1499.004); ranked in the top 48% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as LLM Application Platforms.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SI-10 (Information Input Validation) — see the control section below for these in your framework.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious…

more

HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.

CWE(s)

AI Security AnalysisAI

AI Category
LLM Application Platforms
Risk Domain
N/A
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: huggingface

Related Threats

MITRE ATT&CK Enterprise Techniques

T1499.004 Application or System Exploitation Impact
Adversaries may exploit software vulnerabilities that can cause an application or system to crash and deny availability to users.
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-2026-22807Same product: Vllm Vllm
CVE-2025-66448Same product: Vllm Vllm
CVE-2026-31233Shared CWE-94
CVE-2024-58351Shared CWE-94
CVE-2026-22793Shared CWE-94
CVE-2026-54769Shared CWE-94
CVE-2026-4276Shared CWE-94
CVE-2026-23733Shared CWE-94
CVE-2026-0771Shared CWE-94
CVE-2024-10252Shared CWE-94

Affected Assets

vllm
vllm
≤ 0.22.0

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)

Validate
Prove the fix (OWASP ASVS)
  • V1.3.1

Mitigating Controls (NIST 800-53 r5) AI

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.

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.

Security engineering principles discourage use of assertions for handling untrusted input.

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).

DE.CM-09 partial match
prevents

Runtime monitoring of software can detect assertion-triggered crashes as adverse events.

ID.RA-01 partial match
prevents

Vulnerability identification processes can discover and record reachable-assertion flaws before deployment.

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.

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 in development can detect reachable assertions before release, reducing the likelihood of exploitation.

prevents

Secure development lifecycle mandates defensive coding and input validation that prevent reachable assertions from being triggered by untrusted data.

prevents

Application security requirements can specify that assertions must not be reachable from attacker-controlled inputs.

prevents

Secure architecture principles discourage the use of assertions for runtime error handling that an attacker could exploit.

prevents

Banning unapproved code samples and unauthenticated web services, combined with secure-coding standards and SAST, prevents the dynamic generation or inclusion of attacker-supplied code.

none

Controls that restrict unauthorized or malicious code from being introduced via external networks or removable media limit opportunities for an attacker to inject and execute arbitrary code.

References