CVE-2025-25183
published 2025-02-07CVE-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…
PriorityP410low2.6CVSS 3.1
AVNACHPRLUIRSUCNILAN
EPSS
0.18%
7.3th percentile
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.
Affected
5 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| msrc | cbl2_python3_3.9.19-13_on_cbl_mariner_2.0 | — | — |
| vllm-project | vllm | < 0.7.2 | 0.7.2 |
| vllm | vllm | < 0.7.2 | 0.7.2 |
| vllm | vllm | >= 0 < 0.7.2 | 0.7.2 |
| vllm | vllm | >= 0 < 432117cd1f59c76d97da2eaff55a7d758301dbc7 | 432117cd1f59c76d97da2eaff55a7d758301dbc7 |
CVSS provenance
nvdv3.12.6LOWCVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N
vendor_msrc2.6LOW
vendor_redhat2.6LOW
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
Microsoft
vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache
vendor_msrc·2025-02-11·CVSS 2.6
CVE-2025-25183 [LOW] CWE-354 vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache
vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache
FAQ: Is Azure Linux the only Microsoft product that includes this open-source library and is therefore potentially affected by this vulnerability?
One of the main benefits to our customers who choose to use the Azure Linux distro is the commitment to keep it up to date with the most recent and most secure versions of the open source libraries with which the distro is composed. Microsoft is committed to transparency in this work which is why we began publishing CSAF/VEX in October 2025. See this blog post for more information. If impact to additional products is identified, we will update the CVE to reflect this.
Mariner: Mariner
GitHub_M: GitHub_M
Customer Action Required: Yes
Red Hat
vllm: vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
vendor_redhat·2025-02-06·CVSS 2.6
CVE-2025-25183 [LOW] CWE-916 vllm: vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
vllm: vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
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 usin
OSV
CVE-2025-25183: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs
osv·2025-02-07
CVE-2025-25183 CVE-2025-25183: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs
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 a
GHSA
vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
ghsa·2025-02-06
CVE-2025-25183 [LOW] CWE-354 vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
### Summary
Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior.
### Details
vLLM's 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.
### Impact
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
OSV
vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
osv·2025-02-06
CVE-2025-25183 [LOW] vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
### Summary
Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior.
### Details
vLLM's 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.
### Impact
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
No detection rules found.
No public exploits indexed.
No writeups or analysis indexed.
2025-02-07
Published