CVE-2026-116176

vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by embedding a decode address in the X-Request-Id header. Attackers can make a P2pNcclConnector prefill worker ZMQ-connect to an attacker host, leaking the NCCL...

CVE-2026-116176

A flaw was found in vLLM. This vulnerability allows a remote attacker to trigger a Server-Side Request Forgery SSRF by submitting an HTTP request containing a crafted X-Request-Id header. Because the application extracts network addresses from this header without validation, backend workers can b...

CVE-2026-116176 vLLM 0.9.2 before 0.24.0 SSRF via X-Request-Id in P2pNcclConnector

vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by embedding a decode address in the X-Request-Id header. Attackers can make a P2pNcclConnector prefill worker ZMQ-connect to an attacker host, leaking the NCCL...

EUVD-2026-109437

vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by embedding a decode address in the X-Request-Id header. Attackers can make a P2pNcclConnector prefill worker ZMQ-connect to an attacker host, leaking the NCCL...

CVE-2026-116176

The vLLM library (versions 0.9.2 before 0.24.0) contains a Server-Side Request Forgery (SSRF) vulnerability in the P2pNcclConnector component. An attacker can force outbound connections by embedding a decoded address within the X-Request-Id header. This allows an attacker to make a prefill worker...

WS-2026-0166

vllm 0.9.2 - 0.23.0: P2pNcclConnector parses a host:port from the client-controlled X-Request-Id header and connects to it over ZMQ/NCCL, letting an API caller exfiltrate KV-cache tensors to an attacker host GHSA-vfp2-c8pq-v6h6...

EUVD-2026-92845

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: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the flash late-interaction query cache reaches. Summary On late-interaction /score and /rerank deployments...

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`

Affected - Ecosystem / package: pip / vllm - Affected versions: vLLM ≤ 0.25.1 confirmed on 0.25.1, commit 752a3a504485. The lower bound predates 0.25.1; maintainers can confirm how far back the flash late-interaction query cache reaches. Summary On late-interaction /score and /rerank deployments...

CVE-2026-105755

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 querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

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 each worker's querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

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 each worker's querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755

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 querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755 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 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 querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755 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 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 querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755 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 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 querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

CVE-2026-105755

The vLLM inference and serving engine (prior to version 0.30.0 ) is vulnerable to a cross-request integrity break in its flash late-interaction scoring at the /score and /rerank endpoints. The root cause is that the system derives the query_key value from the caller-controlled X-Request-Id header...

CVE-2026-105755: Authorization Bypass Through User-Controlled Key

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 querykey value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can...

PT-2026-106265

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.30.0 Description In deployments using flash late-interaction scoring, the engine derives worker cache keys for query embeddings from the X-Request-Id header, which is controlled by the caller. A concurrent request that...

PT-2026-93260

A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0. Affected is the function MoRIIOConnectorScheduler.request finished/MoRIIOConnectorWorker.get finished/MoRIIOWrapper. handle release message of the file vllm/distributed/kv transfer/kv connector/v1/moriio/moriio connector.py of the...