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-2026-105756

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cachesalt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the...

CVE-2026-105753

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiver cache never receives the payload if...

PYSEC-2026-4197

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, while the engine receiver cache never receives the payload if...

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 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-2026-105754

The vLLM inference and serving engine (prior to version 0.30.0 ) contains a vulnerability in the /inference/v1/generate endpoint within the disaggregated scale-out path. The root cause is that the system trusts caller-supplied features—specifically in the features.kwargs_data , features.mm_hashes...

CVE-2026-105754

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargsdata field, cache identifiers in the features.mmhashes field, ranges in the...

CVE-2026-105754 vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargsdata field, cache identifiers in the features.mmhashes field, ranges in the...

CVE-2026-105753

The vLLM inference and serving engine is vulnerable to a shared-service availability failure in versions prior to 0.28.0 . The root cause is a desynchronization in the mirrored multimodal LRU cache ; if a request is rejected during multimodal rendering, the frontend sender cache commits a media h...

CVE-2026-105752 vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cachesalt value, placing the continuation prefix in the global unsalted cache...

CVE-2026-105752 vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cachesalt value, placing the continuation prefix in the global unsalted cache...

CVE-2026-105752

The vLLM inference and serving engine is vulnerable in versions prior to 0.30.0 due to a flaw in how Harmony tool continuations are handled via POST /v1/responses requests. The application fails to preserve the cache_salt value when rebuilding the next-turn engine input, causing the continuation ...

CVE-2026-105752 vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cachesalt value, placing the continuation prefix in the global unsalted cache...

Important: Red Hat Security Advisory: Red Hat Single Sign-On 7.6.13 for OpenShift image security update

A new image is available for Red Hat Single Sign-On 7.6.13, running on OpenShift Container Platform 3.10 and 3.11, and 4.3. Red Hat Single Sign-On is an integrated sign-on solution, available as a Red Hat JBoss Middleware for OpenShift containerized image. The Red Hat Single Sign-On for OpenShift...

Important: Red Hat Security Advisory: Red Hat Single Sign-On 7.6.13 security update

A security update is now available for Red Hat Single Sign-On 7.6 from the Customer Portal. Red Hat Product Security has rated this update as having a security impact of Important. A Common Vulnerability Scoring System CVSS base score, which gives a detailed severity rating, is available for each...

undertow-core: Undertow HTTP Server Fails to Reject Malformed Host Headers Leading to Potential Cache Poisoning and SSRF

A flaw was found in the Undertow HTTP server core, which is used in WildFly, JBoss EAP, and other Java applications. The Undertow library fails to properly validate the Host header in incoming HTTP requests.As a result, requests containing malformed or malicious Host headers are processed without...

io.netty/netty-resolver-dns: Netty has Insufficient Bailiwick Validation for NS Records

A flaw was found in Netty's DnsResolveContext. An attacker controlling an authoritative name server for a subdomain can exploit this vulnerability by providing crafted NS records that are insufficiently validated. This allows the attacker to poison the DNS cache for parent domains, bypassing...

CVE-2026-93318

A malicious image can advertise DiffIDs from another image while containing different layer contents. In affected versions, BuildKit could use the advertised DiffIDs to derive cache and snapshot identity without validating that they matched the actual layer contents. If a BuildKit daemon with...

CVE-2026-93318 Cache poisoning via unvalidated image layer DiffIDs

A malicious image can advertise DiffIDs from another image while containing different layer contents. In affected versions, BuildKit could use the advertised DiffIDs to derive cache and snapshot identity without validating that they matched the actual layer contents. If a BuildKit daemon with...