CVE-2025-25183

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.

References

• https://github.com/vllm-project/vllm/pull/12621
• https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7
• https://github.com/python/cpython/pull/99541

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.

CVE-2025-25183 has a CVSS score of 2.6 (Low). The vector is network-reachable, low privileges required, and user interaction required. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.7.2); upgrading removes the vulnerable code path.

Kodem intelligence

We address this problem by initializing hashes in vllm with a value that is no longer constant and predictable. It will be different each time vllm runs. This restores behavior we got in Python versions prior to 3.12.

Using a hashing algorithm that is less prone to collision (like sha256, for example) would be the best way to avoid the possibility of a collision. However, it would have an impact to both performance and memory footprint. Hash collisions may still occur, though they are no longer straight forward to predict.

To give an idea of the likelihood of a collision, for randomly generated hash values (assuming the hash generation built into Python is uniformly distributed), with a cache capacity of 50,000 messages and an average prompt length of 300, a collision will occur on average once every 1 trillion requests.

1. What is CVE-2025-25183? CVE-2025-25183 is a low-severity security vulnerability in vllm (pip), affecting versions < 0.7.2. It is fixed in 0.7.2.
2. How severe is CVE-2025-25183? CVE-2025-25183 has a CVSS score of 2.6 (Low). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
3. Which versions of vllm are affected by CVE-2025-25183? vllm (pip) versions < 0.7.2 is affected.
4. Is there a fix for CVE-2025-25183? Yes. CVE-2025-25183 is fixed in 0.7.2. Upgrade to this version or later.
5. Is CVE-2025-25183 exploitable, and should I be worried? Whether CVE-2025-25183 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
6. What actually determines whether CVE-2025-25183 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
7. How do I fix CVE-2025-25183? Upgrade vllm to 0.7.2 or later.