How severe is CVE-2025-46570?

CVE-2025-46570 has a CVSS 3.x base score of 2.6, rated low severity. It is exploitable over network with high attack complexity, requires low privileges and user interaction. Impact on confidentiality is low, integrity none, and availability none.

Is CVE-2025-46570 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (16th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2025-46570?

CVE-2025-46570 affects Vllm. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2025-46570?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.

Does CVE-2025-46570 have an EU (EUVD) identifier?

Yes. CVE-2025-46570 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-16189.

When was CVE-2025-46570 published?

CVE-2025-46570 was published on 2025-05-29 and last updated on 2026-06-17.

CVE-2025-46570

CVE-2025-46570 is a low-severity vulnerability in Vllm with a CVSS 3.x base score of 2.6. 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-203.

Key facts

Severity: Low (CVSS 3.x base score 2.6)
EPSS exploit prediction: 0% (16th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2025-16189
Weakness: CWE-203
Affected product: Vllm
Published: 2025-05-29
Last modified: 2026-06-17

Description

vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.

Frequently asked questions

What is CVE-2025-46570?: vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.
How severe is CVE-2025-46570?: CVE-2025-46570 has a CVSS 3.x base score of 2.6, rated low severity. It is exploitable over network with high attack complexity, requires low privileges and user interaction. Impact on confidentiality is low, integrity none, and availability none.
Is CVE-2025-46570 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (16th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2025-46570?: CVE-2025-46570 affects Vllm. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2025-46570?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
Does CVE-2025-46570 have an EU (EUVD) identifier?: Yes. CVE-2025-46570 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-16189.
When was CVE-2025-46570 published?: CVE-2025-46570 was published on 2025-05-29 and last updated on 2026-06-17.

References

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…

All CVEs affecting Vllm →

Other CWE-203 (Observable Discrepancy) vulnerabilities

CVE-2019-25337 — Critical (CVSS 9.8): OwnCloud 8.1.8 contains a username enumeration vulnerability that allows remote attackers to discover user accounts by…
CVE-2026-23519 — Critical (CVSS 9.8): RustCrypto CMOV provides conditional move CPU intrinsics which are guaranteed on major platforms to execute in…
CVE-2025-27667 — Critical (CVSS 9.8): Vasion Print (formerly PrinterLogic) before Virtual Appliance Host 22.0.843 Application 20.0.1923 allows Administrative…
CVE-2024-25714 — Critical (CVSS 9.8): In Rhonabwy through 1.1.13, HMAC signature verification uses a strcmp function that is vulnerable to side-channel…
CVE-2024-25191 — Critical (CVSS 9.8): php-jwt 1.0.0 uses strcmp (which is not constant time) to verify authentication, which makes it easier to bypass…
CVE-2024-25190 — Critical (CVSS 9.8): l8w8jwt 2.2.1 uses memcmp (which is not constant time) to verify authentication, which makes it easier to bypass…

Browse all CWE-203 (Observable Discrepancy) vulnerabilities →