CVE-2025-25183
CVE-2025-25183 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-354.
Key facts
- Severity: Low (CVSS 3.x base score 2.6)
- EPSS exploit prediction: 0% (8th percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2025-4074
- Weakness: CWE-354
- Affected product: Vllm
- Published:
- Last modified:
Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions. The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. This issue has been addressed in version 0.7.2 and all users are advised to upgrade. There are no known workarounds for this vulnerability.
Frequently asked questions
- What is CVE-2025-25183?
- vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions. The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. This issue has been addressed in version 0.7.2 and all users are advised to upgrade. There are no known workarounds for this vulnerability.
- How severe is CVE-2025-25183?
- CVE-2025-25183 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 none, integrity low, and availability none.
- Is CVE-2025-25183 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (8th percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2025-25183?
- CVE-2025-25183 affects Vllm. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2025-25183?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround.
- Does CVE-2025-25183 have an EU (EUVD) identifier?
- Yes. CVE-2025-25183 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-4074.
- When was CVE-2025-25183 published?
- CVE-2025-25183 was published on 2025-02-07 and last updated on 2026-06-17.
References
- https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7
- https://github.com/vllm-project/vllm/pull/12621
- https://github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8
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-354 vulnerabilities
- CVE-2025-11543 — Critical (CVSS 9.8): Improper Validation of Integrity Check Value vulnerability in Sharp Display Solutions projectors allows a attacker may…
- CVE-2024-25678 — Critical (CVSS 9.8): In LiteSpeed QUIC (LSQUIC) Library before 4.0.4, DCID validation is mishandled.
- CVE-2023-33668 — Critical (CVSS 9.8): DigiExam up to v14.0.2 lacks integrity checks for native modules, allowing attackers to access PII and takeover…
- CVE-2017-15994 — Critical (CVSS 9.8): rsync 3.1.3-development before 2017-10-24 mishandles archaic checksums, which makes it easier for remote attackers to…
- CVE-2026-49230 — Critical (CVSS 9.1): Improper Validation of Integrity Check Value vulnerability in Apache APISIX. The jwe-decrypt plugin under default…
- CVE-2026-34182 — Critical (CVSS 9.1): Issue Summary: Cryptographic Message Services (CMS) processing fails to perform sufficient input validation on the…