Cyber Resilience

CVE-2026-54234

Vllm ≤ 0.24.0

Public PoC
Published
06 July 2026
Modified
07 July 2026
Patch / advisory
View advisory
CVSS Score v3.1 7.5
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS Score 0.0036 29th percentile
Risk Priority 57 floored blend · peak EPSS

Summary

CVE-2026-54234 is a high-severity Improper Input Validation (CWE-20) vulnerability in Vllm Vllm. Its CVSS base score is 7.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Privilege Escalation (T1068); ranked at the 29th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

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)

A05:2025 Injection

EU & UK References

Vulnerability Data

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which…

more

is then converted to negative one when the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and attention path and crashes the engine worker with a GPU device-side assertion. The same triggering request sequence is reachable through the public gRPC Generate and Abort endpoints, so a remote client that can send generation requests can crash the shared engine worker, aborting concurrent requests and causing a service-wide denial of service for other clients of the deployment until the worker is restarted. This issue is fixed in version 0.24.0.

CWE(s)
CWE-20CWE-1284

Related Threats

MITRE ATT&CK Enterprise Techniques

T1068 Exploitation for Privilege Escalation Privilege Escalation
Adversaries may exploit software vulnerabilities in an attempt to elevate privileges.
attack.mitre.org →
T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
attack.mitre.org →
T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
attack.mitre.org →
T1210 Exploitation of Remote Services Lateral Movement
Adversaries may exploit remote services to gain unauthorized access to internal systems once inside of a network.
attack.mitre.org →
T1212 Exploitation for Credential Access Credential Access
Adversaries may exploit software vulnerabilities in an attempt to collect credentials.
attack.mitre.org →
T1036.001 Invalid Code Signature Stealth
Adversaries may attempt to mimic features of valid code signatures to increase the chance of deceiving a user, analyst, or tool.
attack.mitre.org →
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-34760Same product: Vllm Vllm
CVE-2026-54235Same product: Vllm Vllm
CVE-2025-48944Same product: Vllm Vllm
CVE-2026-56340Same product: Vllm Vllm
CVE-2025-62164Same product: Vllm Vllm
CVE-2026-34756Same product: Vllm Vllm
CVE-2026-53923Same product: Vllm Vllm
CVE-2026-54233Same product: Vllm Vllm
CVE-2026-44222Same product: Vllm Vllm
CVE-2026-44223Same product: Vllm Vllm

Affected Assets

vllm
vllm
≤ 0.24.0

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

—

Detect
Catch it (NIST detect / respond)

—

Harden
Shrink the surface (DISA STIG)
  • 6 hardening rules · 3 OS baselines
Validate
Prove the fix (OWASP ASVS)
  • V6.7.2
  • V1.4.2
  • V2.1.1
  • V2.2.1

Mitigating Controls (NIST 800-53 r5) AI

SA-11 Developer Testing and Evaluation good match

Developer testing and evaluation can discover missing input validation through analysis or test cases.

SI-10 Information Input Validation good match

SI-10 directly requires validity checks on information inputs, structurally preventing improper or missing validation.

SA-15 Development Process, Standards, and Tools partial match

Requiring documented development standards and tools can embed input-validation practices into the engineering process.

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

Secure SDLC practices directly require and enforce input validation during development.

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.

A.8.29 Security testing in development and acceptance mostly match
finds

Testing against a defined set of requirements and using code review plus vulnerability scanning forces validation of inputs and handling of unanticipated conditions, reducing the chance that malformed data will be accepted.

A.8.25 Secure development life cycle partial match
prevents

Secure-coding guidelines and mandatory security testing (including code scans) compel developers to validate and sanitize inputs at design and implementation time, lowering the incidence of malformed or malicious data reaching downstream components.

A.8.26 Application security requirements partial match
prevents

Mandating input controls that include integrity checks and input validation ensures that untrusted data is examined before use, blocking the root cause of many injection and malformed-data weaknesses.

A.8.27 Secure system architecture and engineering principles partial match
prevents

Security-by-design principles explicitly call for data validation and sanitization at every layer, reducing the chance that malformed or malicious input will be processed without scrutiny.

A.8.28 Secure coding partial match
prevents

Requiring language-specific secure coding standards, peer review, SAST and documented mitigation of common programming errors forces validation of all inputs before they are trusted.

A.8.7 Protection against malware none match
none

Regular automated validation of system software and data content, combined with scanning of all inbound files, enforces input validation at the boundary before untrusted content is processed.

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).

RHEL 8 (1 rule)
  • 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-20

References