Cyber Resilience

CVE-2026-5497

DoS in Vllm 0.8.0 – 0.19.0

Public PoCDoS
Published
11 June 2026
Modified
22 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:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS Score 0.0054 43th percentile
Risk Priority 58 floored blend · peak EPSS

Summary

CVE-2026-5497 is a high-severity Uncontrolled Resource Consumption (CWE-400) vulnerability in Vllm Vllm. Its CVSS base score is 7.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Network Denial of Service (T1498); ranked at the 43th percentile by exploit likelihood (below the median); 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 AC-10 (Concurrent Session Control) and SC-5 (Denial-of-service Protection) — see the control section below for these in your framework.

EU & UK References

Vulnerability Data

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas…

more

to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.

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: openai

Related Threats

MITRE ATT&CK Enterprise Techniques

T1498 Network Denial of Service Impact
Adversaries may perform Network Denial of Service (DoS) attacks to degrade or block the availability of targeted resources to users.
T1499 Endpoint Denial of Service Impact
Adversaries may perform Endpoint Denial of Service (DoS) attacks to degrade or block the availability of services to users.
T1499.001 OS Exhaustion Flood Impact
Adversaries may launch a denial of service (DoS) attack targeting an endpoint's operating system (OS).
T1499.003 Application Exhaustion Flood Impact
Adversaries may target resource intensive features of applications to cause a denial of service (DoS), denying availability to those applications.
T1498.001 Direct Network Flood Impact
Adversaries may attempt to cause a denial of service (DoS) by directly sending a high-volume of network traffic to a target.
T1498.002 Reflection Amplification Impact
Adversaries may attempt to cause a denial of service (DoS) by reflecting a high-volume of network traffic to a target.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2026-55646Same product: Vllm Vllm
CVE-2026-34755Same product: Vllm Vllm
CVE-2025-29770Same product: Vllm Vllm
CVE-2026-22773Same product: Vllm Vllm
CVE-2025-30202Same product: Vllm Vllm
CVE-2025-62426Same product: Vllm Vllm
CVE-2025-48956Same product: Vllm Vllm
CVE-2026-34756Same product: Vllm Vllm
CVE-2025-71379Same product: Vllm Vllm
CVE-2026-55514Same product: Vllm Vllm

Affected Assets

vllm
vllm
0.8.0 — 0.19.0

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)
  • 5 hardening rules · 3 OS baselines
Validate
Prove the fix (OWASP ASVS)
  • V15.4.4

Mitigating Controls (NIST 800-53 r5) AI

Directly enforces a hard limit on concurrent sessions, structurally preventing unbounded resource allocation.

SC-5 directly limits the effects of resource-exhaustion events that constitute uncontrolled consumption.

SC-6 enforces explicit allocation limits on resources, structurally preventing the weakness from occurring.

Imposes a limit on consecutive invalid attempts, preventing one specific class of unbounded resource consumption.

Process isolation confines resource consumption to separate domains, reducing blast radius without stopping the root flaw.

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.IR-04 mostly match
prevents

Explicitly requires monitoring and maintaining resource capacity, directly addressing uncontrolled consumption to preserve availability.

DE.CM-09 partial match
prevents

Continuous monitoring of computing resources can detect resource exhaustion but does not itself enforce allocation limits.

PR.IR-03 partial match
prevents

Resilience mechanisms such as avoiding single points of failure indirectly reduce impact of resource exhaustion.

PR.PS-01 partial match
prevents

Hardened configuration baselines can include resource quotas and limits that constrain consumption.

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

Resource-utilization monitoring and alerting on bottlenecks or overloads limits the impact of denial-of-service or resource-exhaustion attacks.

prevents

By continuously monitoring utilization, stress-testing peak loads, and maintaining documented plans to scale or throttle resources, the control directly limits an attacker’s ability to drive a system into uncontrolled resource exhaustion.

finds

Pre-agreed severity-based prioritization and resource allocation during incident triage reduce the likelihood that an attacker-induced resource exhaustion will overwhelm the organization before corrective action is taken.

mitigates

Business-continuity plans that include resource-management controls reduce the likelihood that an attacker can trigger uncontrolled resource consumption by forcing the system into a degraded or fallback state.

mitigates

Defining RTOs and capacity requirements for ICT services during business-impact analysis forces organizations to provision sufficient resources and throttling mechanisms, reducing the likelihood that an attacker can induce denial-of-service through uncontrolled resource consumption.

finds

Early notification of anomalous resource consumption or system malfunctions enables throttling or isolation before availability is lost.

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-248552 OL 8 must be configured so that all network connections associated with SSH traffic terminate after becoming unresponsive. prevents CWE-770
  • V-248553 OL 8 must be configured so that all network connections associated with SSH traffic are terminated after 10 minutes of becoming unresponsive. prevents CWE-770
Oracle Linux 9 (2 rules)
  • V-271710 OL 9 must be configured so that all network connections associated with SSH traffic are terminated after 10 minutes of becoming unresponsive. prevents CWE-770
  • V-271709 OL 9 must be configured so that all network connections associated with SSH traffic terminate after becoming unresponsive. prevents CWE-770
RHEL 8 (1 rule)
  • V-230244 RHEL 8 must be configured so that all network connections associated with SSH traffic terminate after becoming unresponsive. prevents CWE-770

References