Vulnerability 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.
CVSS Score
HIGH
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.8.0, < 0.19.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fPatch
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4ExploitThird Party Advisory
- https://access.redhat.com/security/cve/CVE-2026-5497
- https://bugzilla.redhat.com/show_bug.cgi?id=2487813
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4ExploitThird Party Advisory
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json
FAQ
What is CVE-2026-5497?
CVE-2026-5497 is a vulnerability with a CVSS score of 7.5 (HIGH). 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 processin...
How severe is CVE-2026-5497?
CVE-2026-5497 has been rated HIGH with a CVSS base score of 7.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-5497?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.