CVE-2026-126399
vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames
vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion.
Fixes and workarounds
No remediation reported in collected sources.
Missing remediation information is not evidence that no patch exists.
Affected products and versions
| Product | Versions | Authority |
|---|---|---|
| vllm vllm-project vllm
pypi |
≥ 0.19.0; < 0.31.0 (affected, semver) 0.31.0 (unaffected, semver) Other versions: unaffected |
CNA: VulnCheck |
Version ranges are source assertions. Check the vendor advisory and your installed configuration before determining exposure.
CVSS assessments
| Version / score | Vector | Authority |
|---|---|---|
| 4.0 / 7.1 high |
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N | CNA: VulnCheck |
| 3.1 / 6.5 medium |
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CNA: VulnCheck |
| 4.0 / 7.1 high |
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X | NVD: [email protected] |
| 3.1 / 6.5 medium |
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | NVD: [email protected] |
Exploit evidence
No exploit evidence in collected sources. This is not proof of no exploitation.
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-vxqj-p4gw-9h4cCNA: VulnCheck · vendor-advisory
- https://www.vulncheck.com/advisories/vllm-0.19.0-before-0.31.0-resource-exhaustion-via-request-level-num-framesCNA: VulnCheck · third-party-advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-vxqj-p4gw-9h4c[email protected]
- https://www.vulncheck.com/advisories/vllm-0.19.0-before-0.31.0-resource-exhaustion-via-request-level-num-frames[email protected]
For agents and automation
Read public disclosures for free as Markdown or JSON. Compatible browsers also expose native WebMCP tools to search disclosures, read this page, and discover API access.
Use the ontology-linked Cyber API with x402 pay per request, or a Y2 Pro or Elite API key with the intel:cyber scope.
Endpoints and access details
https://api.y2.dev/api/v2/cyber/cveshttps://api.y2.dev/api/v2/cyber/cves/{cveId}
A workspace owner or admin can create a Pro or Elite API key. Send Authorization: Bearer <Y2_API_KEY> from your trusted agent runtime.
For x402, omit Authorization and read the HTTP 402 payment challenge before signing a retry. Public browser tools do not make payments.