Newly released CVEs across every platform — sleek to read, verbose on demand, and served raw as markdown for AI and agent ingestion. Severity reads as depth: the deeper the contact, the graver the threat.
Depth = severity + exploitation
CVE-2026-116175Medium· 6.5vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls load_audio without the max_duration_s decoded-duration limit. Authenticated attackers can send small compressed aud…
CVE-2026-116174Medium· 5.9vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC Generate and GenerateStream service that forwards unchecked prompt token IDs to EngineCore. Attackers can submit requests with out-of-voc…
CVE-2026-116179High· 7.5vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding num_frames through media_io_kwargs. Attackers can set num_frames to -1 with a larg…
CVE-2026-116177High· 7.5vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust memory because the Nemotron-VL processors globally set Image.MAX_IMAGE_PIXELS to None. Attackers …
CVE-2026-116181Medium· 6.5vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or b…
CVE-2026-116180High· 7.7vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector…
CVE-2026-114049Low· 3.7vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate…
CVE-2026-114051High· 7.5vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthe…
CVE-2026-114054Medium· 6.5vLLM before 0.31.0 contains a cache aliasing vulnerability that allows authenticated attackers to collide shared cache keys by supplying caller-controlled values such as EXIF ImageID or cache_salt. Attackers can set a UUID EXIF ImageID t…
CVE-2026-114053High· 8.1vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients select which revision of a model's dynamic processor code is imported when trust…
CVE-2026-114055High· 7.5vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters by supplying per-request mm_processor_kwargs. Attackers can set large image s…
CVE-2026-109311Medium· 6.5PoCvLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser heap overflow. Authenticated remote attackers can repeatedly upload malformed IAMF containers to /v…
CVE-2026-105775Medium· 4.3PoCA security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/model_executor/layers/mamba/mamba_mixer2.py of the component Completions Request Handler. The manip…
CVE-2026-100653Medium· 6.5PoCvLLM is an inference and serving engine for large language models. In versions from 0.22.1 through 0.28.0, the operator-supplied model revision pin (--revision / --code-revision) is not propagated to several Hugging Face artifact loads f…
CVE-2026-92365Medium· 4.3⚖ disputedA vulnerability was found in vllm-project vllm up to 0.29.0. Affected by this issue is some unknown functionality of the file vllm/v1/sample/thinking_budget_state.py. The manipulation results in inefficient algorithmic complexity. It is …
CVE-2026-92220Medium· 5.3⚖ disputedA 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_tra…
CVE-2026-90878Medium· 4.3PoCA vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template Rendering. This manipulation of the argument chat_template causes resource co…
CVE-2026-90713Low· 3.3PoCA security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipula…
The beta is over. VulnSea now runs at vulnsea.com, every old beta link redirects to the same page, and your account, API keys and watchlists came with it. Plus a round of hardening, faster pages, and new request limits agents should know about.
A summary of everything that shipped over the last two weeks — the whole corpus is open, agents get change feeds, alias resolution and EPSS movers, and the data now includes CVE.org, vendor CSAF, aggregated exploits and per-source scores.
A step-by-step guide to plugging VulnSea into automated and agentic workflows — poll the delta, triage without burning tokens, match an SBOM, and let an MCP-native model do the reasoning.