CVE-2026-5497
CVE-2026-5497 is a high-severity vulnerability in Vllm with a CVSS 3.x base score of 7.5. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-400.
Key facts
- Severity: High (CVSS 3.x base score 7.5)
- EPSS exploit prediction: 1% (42nd percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2026-36217
- Weakness: CWE-400
- Affected product: Vllm
- Published:
- Last modified:
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.
Frequently asked questions
- What is CVE-2026-5497?
- 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.
- How severe is CVE-2026-5497?
- CVE-2026-5497 has a CVSS 3.x base score of 7.5, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is none, integrity none, and availability high.
- Is CVE-2026-5497 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (42nd percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2026-5497?
- CVE-2026-5497 affects Vllm. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2026-5497?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
- Does CVE-2026-5497 have an EU (EUVD) identifier?
- Yes. CVE-2026-5497 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-36217.
- When was CVE-2026-5497 published?
- CVE-2026-5497 was published on 2026-06-11 and last updated on 2026-07-03.
References
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
- https://access.redhat.com/security/cve/CVE-2026-5497
- https://bugzilla.redhat.com/show_bug.cgi?id=2487813
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json
Affected products (1)
- cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
More vulnerabilities in Vllm
- CVE-2025-32444 — Critical (CVSS 10.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and…
- CVE-2026-22778 — Critical (CVSS 9.8): vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid…
- CVE-2025-47277 — Critical (CVSS 9.8): vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4…
- CVE-2024-11041 — Critical (CVSS 9.8): vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses…
- CVE-2026-48746 — Critical (CVSS 9.1): vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in…
- CVE-2025-29783 — Critical (CVSS 9.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use…
Other CWE-400 (Uncontrolled Resource Consumption) vulnerabilities
- CVE-2026-46775 — Critical (CVSS 9.9): Vulnerability in Oracle REST Data Services (component: Core). Supported versions that are affected are 24.2.0-26.1.0.…
- CVE-2025-61303 — Critical (CVSS 9.8): Hatching Triage Sandbox Windows 10 build 2004 (2025-08-14) and Windows 10 LTSC 2021(2025-08-14) contains a…
- CVE-2025-43193 — Critical (CVSS 9.8): The issue was addressed with improved memory handling. This issue is fixed in macOS Sequoia 15.6, macOS Sonoma 14.7.7,…
- CVE-2025-24269 — Critical (CVSS 9.8): The issue was addressed with improved memory handling. This issue is fixed in macOS Sequoia 15.4. An app may be able to…
- CVE-2025-24264 — Critical (CVSS 9.8): The issue was addressed with improved memory handling. This issue is fixed in Safari 18.4, iOS 18.4 and iPadOS 18.4,…
- CVE-2025-24260 — Critical (CVSS 9.8): The issue was addressed with improved memory handling. This issue is fixed in macOS Sequoia 15.4, macOS Sonoma 14.7.5,…
Browse all CWE-400 (Uncontrolled Resource Consumption) vulnerabilities →