CVE-2026-105755: medium-severity vulnerability in vllm-project vllm
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`
Published · Updated
13Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 4.2epss 0.2%
exploitation probability
0.2%top 91% of all CVEs
observed exploitation
nono source reports it
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.
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L
Affected products
vllm-project · vllmRelated CVEs — vllm-project vllm
In the same product, most dangerous first.
CVE-2026-22778CRITICALvLLM leaks a heap address when PIL throws an errorEPSS 11.2%CVE-2026-27893HIGHvLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-outEPSS 1.8%CVE-2025-32444CRITICALvLLM Vulnerable to Remote Code Execution via Mooncake IntegrationEPSS 1.8%CVE-2026-48746CRITICALvLLM: OpenAI auth bypassEPSS 1.2%CVE-2025-47277CRITICALvLLM Allows Remote Code Execution via PyNcclPipe Communication ServiceEPSS 1.0%CVE-2025-62164HIGHVLLM deserialization vulnerability leading to DoS and potential RCEEPSS 0.9%