Cyber Resilience

CVE-2025-25183

Low

Published: 07 February 2025

Published
07 February 2025
Modified
01 July 2025
KEV Added
Patch
CVSS Score v3.1 2.6 CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N
EPSS Score 0.0032 55.8th percentile
Risk Priority 5 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-25183 is a low-severity Improper Validation of Integrity Check Value (CWE-354) vulnerability in Vllm Vllm. Its CVSS base score is 2.6 (Low).

Operationally, ranked in the top 44.2% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Adversarial Attacks risk domain.

EU & UK References

Vulnerability details

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…

more

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.

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Adversarial Attacks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: llms, vllm

Related Threats

Affected Assets

vllm
vllm
≤ 0.7.2

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

addresses: CWE-354

Proper validation of integrity check values is required for reliable tamper detection, directly reducing undetected modification risks.

addresses: CWE-354

Requires validation of integrity check values on every resolution response, directly mitigating tampered or corrupted DNS data.

addresses: CWE-354

Control mandates proper validation of integrity values (checksums) on prepared data, making flawed validation of those checks ineffective for attackers.

addresses: CWE-354

Requires use of proper integrity verification tools, reducing the chance an incorrect check value is accepted.

addresses: CWE-354

Requires proper validation of integrity mechanisms, directly mitigating flawed check-value handling.

References