vLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method
High7.5CVE-2026-5497 · Published Jun 11, 2026 · updated Aug 18, 2026
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| vllm PyPI | >= 0.8.0, < 0.19.0 | 0.19.0 |
Details and references
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 3.0
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
- Severity from
- GitHub (reviewed advisory)
- Weakness
- CWE-400, CWE-770
- Also known as
- CVE-2026-5497, PYSEC-2026-2302
- nvd.nist.gov/vuln/detail/CVE-2026-5497
- github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
- access.redhat.com/errata/RHSA-2026:33524
- access.redhat.com/errata/RHSA-2026:33531
- access.redhat.com/security/cve/CVE-2026-5497
- bugzilla.redhat.com/show_bug.cgi?id=2487813
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2302.yaml
- github.com/vllm-project/vllm
- huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
- security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json
More vLLM advisories
All vLLM| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Jun 10 | vLLM's Artifact Pin Decay allows pinned deployments to load unpinned code, weights, and processors CVE-2026-47155Medium6.5fixed in 0.22.0 | Medium6.5 | 0.22.0 |
| Jun 16 | vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution CVE-2026-41523High7.5fixed in 0.22.0 | High7.5 | 0.22.0 |
| Jun 16 | vLLM: OpenAI auth bypass CVE-2026-48746Critical9.1fixed in 0.22.0 | Critical9.1 | 0.22.0 |
| Jun 17 | vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels CVE-2026-54235Medium6.5fixed in 0.24.0 | Medium6.5 | 0.24.0 |
| Jun 17 | vLLM: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations CVE-2026-12491Medium4.8fixed in 0.24.0 | Medium4.8 | 0.24.0 |
| Jun 17 | vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving CVE-2026-53923Medium7.5fixed in 0.24.0 | Medium7.5 | 0.24.0 |