NetSight

Security Dashboard

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

Reset
159 matching advisories · page 4 of 6Index updated 9 minutes ago · Subscribe · RSS
SeverityIDTitleAffectedAge
medium6.7 CVE-2026-20755 Protection mechanism failure for some LLM Scaler software within Ring 3: User Applications may allow an escalation of privilege. intel · llm-scaler-vllm 2026-08-11 critical GHSA-h8wv-25mv-64f5 Malicious code in vllm-plugins (PyPI)Malware pip · vllm-plugins 2026-07-21 high7.5 CVE-2026-15574 A flaw was found in the vllm-orchestrator-gateway component. 2026-07-13 high7.5 CVE-2026-55574 vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends pip · vllm 2026-07-06 high7.1 CVE-2026-55514 vLLM denial of service via prompt embeds on M-RoPE models pip · vllm 2026-07-06 high7.5 CVE-2026-54234 vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. pip · vllm 2026-07-06 medium6.5 CVE-2026-55646 vLLM: Speech-to-text upload size limit is enforced after full UploadFile read pip · vllm 2026-07-06 high8.8 CVE-2026-54232 vLLM is an inference and serving engine for large language models (LLMs). vllm · vllm 2026-06-22 medium5.3 CVE-2025-71379 vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. pip · vllm 2026-06-20 medium4.8 GHSA-x8xr-mj9x-6h7w Duplicate Advisory: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations pip · vllm 2026-06-17 medium6.5 CVE-2026-54233 vLLM is an inference and serving engine for large language models (LLMs). pip · vllm 2026-06-17 medium5.3 CVE-2026-54236 vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router pip · vllm 2026-06-17 high7.5 CVE-2026-53923 vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving pip · vllm 2026-06-17 medium6.5 CVE-2026-54235 vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels pip · vllm 2026-06-17 medium4.8 CVE-2026-12491 vLLM: image EXIF Rotation & PNG tRNS Transparency Not Normalized, Causing Mismatch Between Model Input and Expectations pip · vllm 2026-06-17 critical9.1 CVE-2026-48746 vLLM is an inference and serving engine for large language models (LLMs). pip · vllm 2026-06-16 high7.5 CVE-2026-41523 vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution pip · vllm 2026-06-16 high7.5 CVE-2026-5497 vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMedi… pip · vllm 2026-06-11 medium6.5 CVE-2026-47155 vLLM's Artifact Pin Decay allows pinned deployments to load unpinned code, weights, and processors pip · vllm 2026-06-10 high8.8 CVE-2026-4944 vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/mo… 2026-05-28 medium5.3 CVE-2026-9540 A vulnerability was identified in vllm-project vllm 0.19.0. pip · vllm 2026-05-26 high8.2 CVE-2026-5817 The vllm-metal inference backend in Docker Model Runner on macOS unconditionally sets trust_remote_code=True when loading model tokenizers, and runs without sa… docker · docker_desktop 2026-05-22 medium6.5 CVE-2026-44223 vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters pip · vllm 2026-05-06 medium6.5 CVE-2026-44222 vLLM is an inference and serving engine for large language models (LLMs). pip · vllm 2026-05-05 medium5.6 CVE-2026-7141 A vulnerability was found in vLLM up to 0.19.0. pip · vllm 2026-04-27 medium6.5 CVE-2026-34755 vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing pip · vllm 2026-04-03 medium5.4 CVE-2026-34753 vLLM is an inference and serving engine for large language models (LLMs). pip · vllm 2026-04-03 medium6.5 CVE-2026-34756 vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server pip · vllm 2026-04-03 medium5.9 CVE-2026-34760 vLLM: Processing differential in multi-channel audio downmixing enables hidden-input/moderation bypass for audio models pip · vllm 2026-04-02 high8.8 CVE-2026-27893 vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out pip · vllm 2026-03-27

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.