CVE-2026-5497Public exploitNetwork attack vector

Unauthenticated server crash via unbounded JPEG frames

Published Jun 11, 2026 · Updated Jun 11, 2026

Uncontrolled resource consumption in vLLM before 0.19.0 allows remote attackers to crash the server via a crafted video/jpeg data URL. The VideoMediaIO.load_base64() method splits the data at every comma and decodes each segment as a JPEG frame without enforcing the configured frame limit. An exposed OpenAI-compatible chat completions API is sufficient, and processing thousands of frames in one unauthenticated request can exhaust server memory and terminate service.

CVSS severity7.5
High
EPSS probability0.54%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Uncontrolled resource consumption in vLLM before 0.19.0 allows remote attackers to crash the server via a crafted video/jpeg data URL. The VideoMediaIO.load_base64() method splits the data at every comma and decodes each segment as a JPEG frame without enforcing the configured frame limit. An exposed OpenAI-compatible chat completions API is sufficient, and processing thousands of frames in one unauthenticated request can exhaust server memory and terminate service.

The record

CVE
CVE-2026-5497
Published
Jun 11, 2026
Updated
Jun 11, 2026
Vendor
vLLM Project
Product
vLLM
Classifications
CWE-400, CWE-770, T1499
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Jun 11, 2026CVE publishedPublication date reported by the CVE source.
  2. Jun 11, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=unspecified <0.19.0

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

vLLM Project · vLLMversion=unspecified <0.19.0

Published CVSS scores

7.5GitHub Advisory DatabaseCVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-400Uncontrolled Resource Consumption
CWE-770Allocation of Resources Without Limits or Throttling
T1499Endpoint Denial of Service

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo