Unrated
CVE-2026-105922
Vulnerability archive
Understand vulnerabilities. Protect your applications.
Discover which vulnerabilities affect your technologies and how to fix them. Explore clear explanations, affected versions and practical recommendations - from CMS platforms and plugins to application libraries.
Vulnerability archive 100
Reset filters
Low
CVE-2026-105752
vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle
Medium
CVE-2026-105758
vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach
Medium
CVE-2026-105760
vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
Medium
CVE-2026-105754
vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features
Medium
CVE-2026-105756
vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service
Medium
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`
Medium
CVE-2026-105757
vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites)
Medium
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
Medium
CVE-2026-69147
vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation
Medium
CVE-2026-57173
vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
High
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
Unrated
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,
High
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
Critical
CVE-2026-61732
Decepticon: Role-boundary forgery via ChatML special-token literals in web crawl output composed into LLM context
Unrated
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
Unrated
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
Unrated
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
Unrated
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
Unrated
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
Medium
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
Medium
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
Medium
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
Unrated
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
Know which vulnerabilities affect your application
With the DockRay integration and software inventory enabled, DockRay checks reported component versions against known vulnerabilities and notifies you about confirmed matches. Coverage depends on the supported technology and available advisory data.