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`
Exact source revision recorded 23 Oct 2026 15:48:27 UTC. It does not establish the source's current position. Latest evidence.
cve-program · CVE-2026-105755
PublishedvLLM 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.
- Source published
- 5 Oct 2026 22:47:54 UTC
- Source modified
- 6 Oct 2026 17:55:21 UTC
- Observed here
- 23 Oct 2026 15:48:27 UTC
- Source terms
- CVE Program Terms of Use
Original source record · Cite this exact observation · Complete original publisher JSON
This view projects the publisher's source fields for reading; the original JSON retains additional fields and CVE enrichment containers. Attribution: cve-program · CVE Program Terms of Use. Source text is retained; field grouping and change labels are provided by ChangeIntel.
CVSS 3.1 · 4.2 CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L