Strix
26.1K

CVE-2026-5497

HIGHCVSS 7.5/10EPSS 0.42%

Last modified

CVE-2026-5497 is a high-severity vulnerability rated 7.5/10 on the CVSS scale. 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. EPSS estimates a 0.42% chance of exploitation in the next 30 days.

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.

Metrics

CVSS 3.0
7.5/10

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

EPSS Probability
0.42%

33.9th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

VendorProductVersions
VllmVllm>= 0.8.0, < 0.19.0

References

Timeline

Published
Last Modified
Status
Analyzed

Frequently Asked Questions

What is CVE-2026-5497?
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.
How severe is CVE-2026-5497?
CVE-2026-5497 has a CVSS score of 7.5/10 (HIGH severity). The EPSS model estimates a 0.42% probability of exploitation in the next 30 days.
How do I fix CVE-2026-5497?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

Are you affected by CVE-2026-5497?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST