CVE-2026-5497
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | >= 0.8.0, < 0.19.0 | 0.19.0 |
Affected products
4Patches
Vulnerability mechanics
References
10- github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395nvdPatchWEB
- huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4nvdExploitThird Party AdvisoryWEB
- github.com/advisories/GHSA-wcwg-c5fc-9vrcghsaADVISORY
- nvd.nist.gov/vuln/detail/CVE-2026-5497ghsaADVISORY
- access.redhat.com/errata/RHSA-2026:33524ghsaWEB
- access.redhat.com/errata/RHSA-2026:33531ghsaWEB
- access.redhat.com/security/cve/CVE-2026-5497ghsaWEB
- bugzilla.redhat.com/show_bug.cgighsaWEB
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2302.yamlghsaWEB
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.jsonghsaWEB
News mentions
0No linked articles in our index yet.