vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank` (vllm-project vllm)
At a glance
- Source
- NVD
- EPSS
- EPSS 0.20 % · percentile 10 ()
- State
- PUBLISHED
- Published
- Updated
- Assigner
- GitHub_M
- NVD status
- Analyzed
Description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.
Weaknesses (CWE)
- CWE-639 — Authorization Bypass Through User-Controlled Key
References
Scores
| Version | Score | Vector | Scored by |
|---|---|---|---|
| CVSS 3.1 | MEDIUM 4.2 | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L | GitHub_M |
| CVSS 3.1 | MEDIUM 4.2 | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L | NVD · security-advisories@github.com (Secondary) |
Advisories
- GHSA-2phq-3phc-84px — vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`
- PYSEC-2026-4198 — vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives e
European references
- ENISA EUVD · EUVD-2026-92845
- GCVE · GCVE-0-2026-105755
Affected configurations (NVD CPE)
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*< 0.30.0
Affected products
| Product | Versions |
|---|---|
| vllm-project · vllm | affected < 030.0 |
Sources
| Source | Licence |
|---|---|
| CVE List (CVEProject cvelistV5) | CVE Program Terms of Use |
| EPSS (FIRST.org) | FIRST — attribution requested |
| ENISA EUVD | ENISA — reproduction authorised, source acknowledged |
| NVD (NIST) via fkie-cad/nvd-json-data-feeds | Public domain — this product uses data from the NVD API but is not endorsed or certified by the NVD |