NetSight

Security Dashboard

A live picture of new vulnerabilities, flaws exploited in the wild and malicious packages.

Reset
159 matching advisories · page 2 of 6Index updated 2 minutes ago · Subscribe · RSS
SeverityIDTitleAffectedAge
high7.5 GHSA-hfwf-hgvp-4rr8 Duplicate Advisory: vLLM vulnerable to remote denial of service through forged multimodal UUID cache desynchronization pip · vllm 32 days ago high7.5 CVE-2026-114055 vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters… pip · vllm 32 days ago medium6.5 CVE-2026-114054 vLLM before 0.31.0 contains a cache aliasing vulnerability that allows authenticated attackers to collide shared cache keys by supplying caller-controlled valu… vllm · vllm 32 days ago high8.1 CVE-2026-114053 vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients se… pip · vllm 32 days ago high7.5 CVE-2026-114052 vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-c… vllm · vllm 32 days ago high7.5 CVE-2026-114051 vLLM 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 di… vllm · vllm 32 days ago high7.5 CVE-2026-114050 vLLM before 0.31.0 uses a client-supplied multimodal uuid verbatim as cache identity with no consistency check on cache hits, allowing engine crashes. pip · vllm 32 days ago low3.7 CVE-2026-114049 vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stal… vllm · vllm 32 days ago medium6.5 CVE-2026-109311 vLLM 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. vLLM 40 days ago medium4.3 CVE-2026-105922 A security flaw has been discovered in vllm-project vLLM up to 0.31.0. vllm · vllm 46 days ago medium4.3 CVE-2026-105775 A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. vllm-project vLLM 46 days ago medium5.3 CVE-2026-105760 vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion pip · vllm 47 days ago medium5.9 CVE-2026-105759 vLLM is an inference and serving engine for large language models. vllm · vllm 47 days ago medium5.3 CVE-2026-105758 vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach pip · vllm 47 days ago medium6.5 CVE-2026-105757 vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites) pip · vllm 47 days ago medium6.5 CVE-2026-105756 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service pip · vllm 47 days ago medium6.5 CVE-2026-105754 vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features pip · vllm 47 days ago medium6.5 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 pip · vllm 47 days ago low3.1 CVE-2026-105752 vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle pip · vllm 47 days ago medium4.2 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` pip · vllm 47 days ago medium5.3 CVE-2026-103241 A flaw has been found in vllm-project vLLM up to 0.26.0. vllm · vllm 52 days ago medium6.5 CVE-2026-100654 vLLM before 0.29.0 accepts user-controlled stop_token_ids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates o… vllm · vllm 56 days ago medium6.5 CVE-2026-100653 vLLM is an inference and serving engine for large language models. vllm · vllm 56 days ago medium5.9 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… vllm · vllm 56 days ago medium6.5 CVE-2026-100651 vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. vllm · vllm 56 days ago medium6.5 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 c… vllm · vllm 56 days ago low3.7 CVE-2026-100649 vLLM before 0.29.0 contains a resource-limit bypass vulnerability in PyNvVideoCodec decoder allocation where sampler subclass shadowing allows independent coun… vllm · vllm 56 days ago medium5.3 CVE-2026-100648 vllm before 0.29.0 fails to enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB limit in multimodal chat audio decoding, allowing unauthenticated clients to bypass file si… vllm · vllm 56 days ago medium5.3 CVE-2026-100647 vLLM versions before 0.29.0 contain a denial-of-service vulnerability in the cache_salt parameter accepted on OpenAI-compatible and Anthropic API endpoints, wh… vllm · vllm 56 days ago high7.5 GHSA-8qpc-6rxx-4pxf Duplicate Advisory: vllm p2p never connected zmq_exhaustion pip · vllm 2026-09-22

Get notifications

Subscribe to new vulnerabilities and early warnings from the last seven days. Pick what matters to your stack and copy the address into any feed reader. More filters appear when you pick a type.

Format:
Open feed

Early warnings are advisories that are published before or without a CVE number, for example malicious packages, advisories with a CVE still pending and reports that are not reviewed yet. Confidence says how well an entry is checked: high, medium or low.

About this dashboard

The dashboard keeps its own index of security advisories and refreshes it every 30 minutes. It merges the national vulnerability database, package advisories, malware reports and the catalog of vulnerabilities that are exploited in the wild into one record per issue. Reports about the same flaw are combined, so nothing is listed twice.

Open any entry for the full record: description, severity vector, affected packages and versions, fixed versions, weakness class, exploitation probability and references.

Sources: the GitHub Advisory Database (reviewed advisories, malware reports and unreviewed reports), the National Vulnerability Database, the CVE Program (cve.org) for brand-new records, the OpenSSF malicious packages list, the CISA catalog of Known Exploited Vulnerabilities and Microsoft's blocklist of malicious VS Code extensions. Every entry names its sources on its detail page.

This product uses the NVD API but is not endorsed or certified by the NVD.

Reading the figures

  • Threat level: a rating computed from three numbers shown next to it: critical advisories in the last 24 hours, vulnerabilities newly confirmed as exploited this week and malware reports this week. It is a quick orientation, not an official warning level.
  • Severity: scores from 9.0 are critical, 7.0 to 8.9 high, 4.0 to 6.9 medium and 0.1 to 3.9 low. Severity describes how bad a flaw is in general. It does not know whether the component is reachable in your environment.
  • Known exploited: exploitation has been observed in real attacks. These are the entries to patch first. Entries with a fix deadline show how many days are left.
  • Early warnings: advisories that appear before or without a CVE number, for example malicious packages, reviewed advisories with a CVE still pending and reports that are not reviewed yet.
  • Priority queue: critical and high advisories of the last 7 days and everything newly exploited, ordered by exploitation status, severity and score.

Questions

Where does the data come from?
From public vulnerability databases, package advisories and the catalog of exploited vulnerabilities. NetSight collects them into its own index every 30 minutes and merges duplicates.
How do I check whether I am affected?
Search for your product or package name, open the record and compare your installed version with the affected and fixed versions. A product name alone does not mean your version is affected.
What does known exploited mean?
Exploitation of this vulnerability has been observed in real attacks. Such entries carry a date they were confirmed and, where one exists, a deadline for applying the fix.
What is an early warning?
An advisory that is published before or without a CVE number, such as a malicious package or a reviewed advisory whose CVE is still pending. They give you a head start, but the details can change.
Is a high severity always more urgent than a low one?
No. Severity measures technical impact in general. Exposure of the affected system, observed exploitation and the exploitation probability matter as much.
Can I follow new advisories automatically?
Yes. Use the notification builder further down to create an RSS, Atom or JSON feed filtered by severity, technology, ecosystem or exploitation status.