Staging Environment: Content and features may be unstable or change without notice.
Advisory details: pypa / vllm/PYSEC-2025-53
Advisory ID pypa/vllm/PYSEC-2025-53
Aliases CVE-2025-46570
GHSA-4qjh-9fv9-r85r
PYSEC-2025-53
Summary vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.
Status Published
Exploitability 0.5
Weighted Severity 0.0
Risk
Affected and Fixed Packages Package Details
Introduced and Fixed Package Commit Patches Package Commit Patches Details
Weaknesses (0)
There are no known CWE.
System Score Found at
There are no known severity scores.
Reference id Reference type URL
https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
https://github.com/vllm-project/vllm/pull/17045
https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
No exploits are available.

No EPSS data available for this advisory.

Patch URL
There are no known patches.
There are no known vectors.

Vector: SSVCv2/E:N/A:N/T:P/P:M/B:A/M:M/D:T/2025-05-29T18:04:57Z/

Decision: Track

Source URL: https://github.com/cisagov/vulnrichment/blob/develop/2025/46xxx/CVE-2025-46570.json

Source Advisory: vulnrichment/CVE-2025-46570

View SSVC decision tree 
[{'Exploitation': 'none'},
 {'Automatable': 'no'},
 {'Technical Impact': 'partial'},
 {'Mission Prevalence': 'minimal'},
 {'Public Well-being Impact': 'material'},
 {'Mission & Well-being': 'medium'}]