CVE-2026-5497 Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm
An attacker can cause a denial of service in vLLM by sending a crafted request with excessive JPEG frames, leading to memory exhaustion.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-5497?
CVE-2026-5497 is a high-severity denial of service vulnerability in Vllm Vllm, published on 11 Jun 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Which versions are affected by CVE-2026-5497?
3 open source packages ship an affected version, including vllm. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
vllm PyPI | From 0.8.0 | 0.19.0 |
vllm PyPI | From 0.8.0 | 0.19.0 |
vllm PyPI | From 0.8.0 | 0.19.0 |
Products include Vllm Vllm.
How do I fix CVE-2026-5497?
Upgrade vllm to 0.19.0 or later.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-5497 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-5497 exists.
Other vulnerabilities in Vllm Vllm
- CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration
- CVE-2026-22778 vLLM leaks a heap address when PIL throws an error
- CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
- CVE-2024-11041 Remote Code Execution in vllm-project/vllm
- CVE-2026-48746 vLLM: OpenAI auth bypass
Sources
Also known as GHSA-wcwg-c5fc-9vrc, PYSEC-2026-2302.