CVE-2025-46570 json
vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel
published 2025-05-28 17 mo ago modified 2026-08-07 3 mo ago also EUVD-2025-16189 , GHSA-4qjh-9fv9-r85r , PYSEC-2025-53
- cvss
- 2.6
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 37%
- public exploits
- 0
- none known
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.
Patch / fix
- pypi vllm 0.9.0
- vllm-project vllm 0.9.0
- vllm vllm 0.9.0
- github.com/vllm-project/vllm@77073c7 commit
- github.com/vllm-project/vllm#17045 pull request
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2025-46570 updated cvss 2.6
vllm: vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel
-
Red Hat AI Inference Server rhaiis/vllm-cuda-rhel9, rhaiis/vllm-rocm-rhel9 Red Hat Enterprise Linux AI (RHEL AI) rhelai1/ui-rhel9, rhelai1/bootc-amd-rhel9, rhelai1/bootc-intel-rhel9, rhelai1/bootc-nvidia-rhel9, rhelai1/bootc-azure-amd-rhel9, rhelai1/instructlab-amd-rhel9, +5 moreaffected: workaround, no fix available “Fix deferred”
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
- Assessed
- 17 mo ago
Exploit prediction
0.43% chance of exploitation in the next 30 days, higher than 37% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 2.6 | CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N |
| GitHub | 3.1 | 2.6 | CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | vllm | <0.9.0 |
0.9.0 |
Affected products
- vllm-project vllm
Classification
References
-
github.com
/vllm-project/vllm/pull/17045
web, issue-tracking, vendor-advisory, report
-
github.com
/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
web, patch
-
github.com
/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
web, vendor-advisory, advisory
-
nvd.nist.gov
/vuln/detail/CVE-2025-46570
advisory
-
github.com
/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-53.yaml
web
-
github.com
/vllm-project/vllm
package
Sources
- CVE List CVE-2025-46570
- GitHub Advisory GHSA-4qjh-9fv9-r85r
- NVD CVE-2025-46570
- OSV PYSEC-2025-53
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.