CVE Watch5 oct 2026

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

CVSS

4.2

Medio

EPSS

—

KEV

—

Exploit Today

0-100

Publicado: 5 oct 2026 · Última mod.: 5 oct 2026 · CWE-639

EPSS · 30d

Sin historial EPSS suficiente todavía.

Descripción técnica

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.

Referencias oficiales

CVEs relacionados

CVECVSSEPSSKEVRExplotTítuloVis.

CVE-2026-1058365.4 MED

—

———QloApps through 1.7.0 contains an authorization bypass vulnerability in AdminProductsController::ajaxProcessBulkUpdateRooms that allows hotel-restricted back-office employees to modify rooms of other hotels. Attackers can submit foreign room IDs in the id_rooms parameter to change status, floor, comments, or inactive dates, disrupting availability and bookings.5h CVE-2026-397566.5 MED

—

———Unauthenticated Insecure Direct Object References (IDOR) in Wappointment <= 2.7.7 versions.7h CVE-2026-325766.5 MED

—

———Customer Insecure Direct Object References (IDOR) in Faktur Pro for WooCommerce <= 3.2.1 versions.7h CVE-2026-1055724.3 MED

—

———A vulnerability has been found in PickMall Lilishop up to 4.2.4. This affects an unknown function of the file /buyer/trade/receipt of the component Buyer Invoice List. Such manipulation of the argument memberId leads to authorization bypass. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. The project was informed of the problem early through an issue report but has not responded yet.15h CVE-2026-1057617.1 ALT

—

——0Dify is an open-source LLM app development platform. Prior to 1.16.0, the PUT /console/api/apps/<app_id>/server endpoint in api/controllers/console/app/mcp_server.py used AppMCPServerController.put() to retrieve an AppMCPServer by the client-supplied server ID without verifying that the server belonged to the requested application and tenant. An authenticated workspace member could therefore change another application's MCP server status and parameters, potentially redirecting data or disabling the service. This issue is fixed in version 1.16.0.19h CVE-2026-1057546.5 MED

—

——0vLLM 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.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.19h