CVE-2026-5497
highpriority · track · 0EPSS 0.005 · 45 %ileDEEUUSEPSS · scored 2026-10-27
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · medium–high · 6.9–7.5
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (5)
Products and version ranges known to be affected.
advisories (3)
Vendor and ecosystem advisories describing this.
- WID-SEC-W-2026-1897vllm: Mehrere SchwachstellenDeutsch2026-06-11csaf · cert_bundDE
Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um Sicherheitsmaßnahmen zu umgehen, einen Denial-of-Service-Zustand zu verursachen, Daten zu manipulieren oder vertrauliche Informationen offenzulegen.
- GHSA-wcwg-c5fc-9vrcvLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method2026-06-11ghsa · osvUS
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.
- PYSEC-2026-23022026-06-11vendor · osvUS
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.
also known as (6)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (9)
External citations — patches, advisories, analysis.
- https://github.com/vllm-project/vllm/releasesPatchcnnvd
- https://nvd.nist.gov/vuln/detail/CVE-2026-5497cnnvd
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395enisa_euvd
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4enisa_euvd
- https://access.redhat.com/security/cve/CVE-2026-5497nvd
- https://bugzilla.redhat.com/show_bug.cgi?id=2487813nvd
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395Patchnvd
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4ExploitThird Party Advisorynvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan