CVE-2025-46560
CVE-2025-46560 is a medium-severity vulnerability in Vllm with a CVSS 3.x base score of 6.5. 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-1333.
Key facts
- Severity: Medium (CVSS 3.x base score 6.5)
- EPSS exploit prediction: 0% (34th percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2025-12671
- Weakness: CWE-1333
- Affected product: Vllm
- Published:
- Last modified:
Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.
Frequently asked questions
- What is CVE-2025-46560?
- vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.
- How severe is CVE-2025-46560?
- CVE-2025-46560 has a CVSS 3.x base score of 6.5, rated medium severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is none, integrity none, and availability high.
- Is CVE-2025-46560 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (34th percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2025-46560?
- CVE-2025-46560 affects Vllm. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2025-46560?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
- Does CVE-2025-46560 have an EU (EUVD) identifier?
- Yes. CVE-2025-46560 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-12671.
- When was CVE-2025-46560 published?
- CVE-2025-46560 was published on 2025-04-30 and last updated on 2026-06-17.
References
- https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197
- https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg
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-1333 vulnerabilities
- CVE-2026-35458 — Critical (CVSS 9.8): Gotenberg is an API for converting document formats. In 8.29.1 and earlier, Gotenberg uses dlclark/regexp2 to compile…
- CVE-2023-29486 — Critical (CVSS 9.8): An issue was discovered in Heimdal Thor agent versions 3.4.2 and before 3.7.0 on Windows, allows attackers to bypass…
- CVE-2026-25547 — Critical (CVSS 9.2): @isaacs/brace-expansion is a hybrid CJS/ESM TypeScript fork of brace-expansion. Prior to version 5.0.1,…
- CVE-2023-29487 — Critical (CVSS 9.1): An issue was discovered in Heimdal Thor agent versions 3.4.2 and before on Windows and 2.6.9 and before on macOS,…
- CVE-2026-47138 — High (CVSS 8.7): Parse Server is an open source backend that can be deployed to any infrastructure that can run Node.js. Prior to…
- CVE-2025-6998 — High (CVSS 8.7): ReDoS in strip_whitespaces() function in cps/string_helper.py in Calibre Web and Autocaliweb allows unauthenticated…