Nicht bewertet
CVE-2026-105922
Schwachstellenarchiv
Schwachstellen verstehen. Anwendungen schützen.
Erfahren Sie, welche Schwachstellen Ihre Technologien betreffen und wie Sie diese beheben. Hier finden Sie verständliche Erklärungen, betroffene Versionen und konkrete Empfehlungen - von CMS und Plugins bis zu Anwendungsbibliotheken.
Schwachstellenarchiv 100
Filter zurücksetzen
Niedrig
CVE-2026-105752
vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle
Mittel
CVE-2026-105758
vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach
Mittel
CVE-2026-105760
vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
Mittel
CVE-2026-105754
vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features
Mittel
CVE-2026-105756
vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service
Mittel
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`
Mittel
CVE-2026-105757
vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)
Mittel
CVE-2026-105753
vLLM: Mirrored multimodal IPC caches desync after a rejected request — a later request reusing the same media hash trips a receiver assertion in the engine core
Mittel
CVE-2026-69147
vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation
Mittel
CVE-2026-57173
vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
Hoch
CVE-2026-103241
A flaw has been found in vllm-project vLLM up to 0.26.0. This vulnerability affects unknown code of the file rust/src/parser/src/unified/gemma4.rs of the component Gemma4UnifiedParser. Executing a man
Nicht bewertet
CVE-2026-100650
vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB,
Hoch
CVE-2026-100652
vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. A
Kritisch
CVE-2026-61732
Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context
Nicht bewertet
CVE-2026-94625
vLLM through 0.29.0 contains a resource exhaustion vulnerability in MooncakeConnector where rejected prefill requests create ownerless transfer placeholders that are never reclaimed. Attackers can sen
Nicht bewertet
CVE-2026-94623
vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion request
Nicht bewertet
CVE-2026-94626
vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbit
Nicht bewertet
CVE-2026-94624
vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can s
Nicht bewertet
CVE-2026-94622
vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments. Attackers can send requests with incomple
Mittel
CVE-2026-93989
vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token i
Mittel
CVE-2026-93840
vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the o
Mittel
CVE-2026-93841
vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary
Nicht bewertet
CVE-2026-93592
vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative to
Erkennen Sie Schwachstellen in Ihrer Anwendung
Mit der DockRay-Integration und aktivierter Softwareinventarisierung prüft DockRay gemeldete Komponentenversionen auf bekannte Schwachstellen und benachrichtigt Sie über bestätigte Treffer. Die Abdeckung hängt von der unterstützten Technologie und den verfügbaren Meldungen ab.