Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
HIGH severity

CVE-2026-5497 — vllm

HIGHFix: vllm-project/vllm@58ee614

CVE-2026-5497 is a high-severity (CVSS 7.5) Uncontrolled Resource Consumption vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.

Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm

Also known asGHSA-wcwg-c5fc-9vrcPYSEC-2026-2302
Published
Jun 11, 2026
Updated
Aug 18, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Sep 28, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

Proof-of-concept exploit code exists

  • CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
  • CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-5497.

EPSS Exploitation Probability

via FIRST.org ↗
0.9%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs58th percentile — riskier than 58% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

CVE-2026-5497 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.

Where this sits among everything scored

Of 382,205 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.

Real-World Exposure

1 pkg affected
🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

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 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.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllm≥ 0.8.0&&< 0.19.00.19.0pip install --upgrade 'vllm==0.19.0'

Affected Products

1 product · 1 configurations
Application
vllmvllm
≥ 0.8.0 && < 0.19.0
range

Detection & mitigation playbook

Open-source dependency

  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update vllm to 0.19.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-5497 is resolved across your whole dependency graph.

  3. Workarounds

    Cap what an attacker can consume: apply request size, rate and timeout limits in front of the affected component, and run it with memory and CPU limits so exhaustion degrades one worker rather than the whole service.

Fixing This On Your OS

If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.

Red HatImportant
Workaround published by Red Hat
Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.
Source: Red Hat security advisory for CVE-2026-5497 (CC BY 4.0)
ProductFixed inAdvisory
Red Hat AI Inference Server 3.4rhaii/vllm-spyre-rhel9:1789681201RHSA-2026:69464
Red Hat AI Inference Server 3.4rhaii/vllm-cpu-rhel9:1789681128RHSA-2026:69466
Red Hat AI Inference Server 3.4rhaii/vllm-cuda-rhel9:1789681126RHSA-2026:69467
Red Hat AI Inference Server 3.4rhaii/vllm-rocm-rhel9:1789681126RHSA-2026:69469
Red Hat AI Inference Server 3.4rhaii/vllm-cpu-rhel9:1790075793RHSA-2026:70965
Red Hat AI Inference Server 3.4rhaii/vllm-spyre-rhel9:1790076141RHSA-2026:70969
Red Hat AI Inference Server 3.4rhaii/vllm-cuda-rhel9:1790090131RHSA-2026:70979
Red Hat AI Inference Server 3.4rhaii/vllm-rocm-rhel9:1790109620RHSA-2026:70995

Frequently Asked Questions

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 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 vu
O3 Security · Impact-Aware SCA

Is CVE-2026-5497 in your dependencies?

Find it across PyPI, including transitive dependencies.

Scan my dependencies How O3 SCA works
CVE-2026-5497: vllm DoS — Fixed in 0.19.0 | O3 Security