Vulnerability database · updated every 15 minutes

New vulnerabilities in the software websites run.

CVEs and security advisories for WordPress, its plugins and themes, npm, PyPI and the servers behind websites, merged from NVD, the CVE Program, GitHub, OSV.dev and WPVulnerability, with CISA's list of the ones attackers exploit.

Free · right away or once a day · unsubscribe in one click
Tracked
55,388
Published in 7 days
1,884
Critical in 30 days
489
Actively exploited
542
Clear filters

Results for “vLLM”

169 vulnerabilities
  1. Medium 6.5

    CVE-2025-61620 · vLLM

    Resource-Exhaustion (DoS) through chat_template / chat_template_kwargs in OpenAI-Compatible Server

    Published 7 Oct 2025 · Fixed in 0.11.0 · Project advisories (GitHub)
  2. High 7.5

    CVE-2025-59425 · vLLM

    API key authentication vulnerable to timing attack

    Published 7 Oct 2025 · Fixed in 0.11.0 · NVD, Project advisories (GitHub)
  3. High 7.5

    CVE-2025-48956 · vLLM

    vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it…

    Published 21 Aug 2025 · Fixed in 0.10.1.1 · NVD
  4. Medium 6.5

    CVE-2025-48944 · vLLM

    vLLM is an inference and serving engine for large language models (LLMs). In version 0.8.0 up to but excluding 0.9.0, the vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the…

    Published 30 May 2025 · Fixed in 0.9.0 · NVD
  5. Medium 6.5

    CVE-2025-48943 · vLLM

    vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

    Published 30 May 2025 · Fixed in 0.9.0 · NVD
  6. Medium 6.5

    CVE-2025-48942 · vLLM

    vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.

    Published 30 May 2025 · Fixed in 0.9.0 · NVD
  7. Medium 6.5

    CVE-2025-48887 · vLLM

    vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to…

    Published 30 May 2025 · Fixed in 0.9.0 · NVD
  8. High 7.3

    CVE-2025-46722 · vLLM

    vLLM is an inference and serving engine for large language models (LLMs). In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata…

    Published 29 May 2025 · Fixed in 0.9.0 · NVD
  9. Low 2.6

    CVE-2025-46570 · vLLM

    vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has…

    Published 29 May 2025 · Fixed in 0.9.0 · NVD
  10. Critical 9.8

    CVE-2025-47277 · vLLM

    vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed…

    Published 20 May 2025 · Fixed in 0.8.5 · NVD
  11. High 8.0

    CVE-2025-30165 · vLLM

    vLLM is an inference and serving engine for large language models. In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a `SUB` ZeroMQ socket and connect to an `XPUB` socket on the primary vLLM host. When data is received on this `SUB` socket, it is deserialized with `pickle`. This is unsafe, as it can be…

    Published 6 May 2025 · NVD
  12. High 7.5

    CVE-2025-46560 · vLLM

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to…

    Published 30 Apr 2025 · Fixed in 0.8.5 · NVD
  13. Critical 9.8

    CVE-2025-32444 · vLLM

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were set to listen on all network interfaces, increasing the likelihood that an attacker…

    Published 30 Apr 2025 · Fixed in 0.8.5 · NVD
  14. High 7.5

    CVE-2025-30202 · vLLM

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.5.2 and prior to 0.8.5 are vulnerable to denial of service and data exposure via ZeroMQ on multi-node vLLM deployment. In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL…

    Published 30 Apr 2025 · Fixed in 0.8.5 · NVD
  15. Critical 9.8

    CVE-2024-11041 · vLLM

    vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload to the MessageQueue, causing the victim's machine to execute arbitrary code.

    Published 20 Mar 2025 · NVD
  16. Critical 9.0

    CVE-2025-29783 · vLLM

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed…

    Published 19 Mar 2025 · Fixed in 0.8.0 · NVD
  17. Medium 6.5

    CVE-2025-29770 · vLLM

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. The outlines library is one of the backends used by vLLM to support structured output (a.k.a. guided decoding). Outlines provides an optional cache for its compiled grammars on the local filesystem. This cache has been on by default in vLLM. Outlines is also available by default through the OpenAI compatible…

    Published 19 Mar 2025 · Fixed in 0.8.0 · NVD
  18. Low 2.6

    CVE-2025-25183 · vLLM

    vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable…

    Published 7 Feb 2025 · Fixed in 0.7.2 · NVD
  19. High 8.8

    CVE-2025-24357 · vLLM

    vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in…

    Published 27 Jan 2025 · Fixed in 0.7.0 · NVD

Where it comes from

The list holds every advisory UpHeron reads for the software it watches: WordPress and every plugin and theme its plugin reports, the packages in monitored repositories and manifests, and the servers and frameworks found on monitored websites. One vulnerability from several sources is one entry, under its CVE.

  • NVD, the US National Vulnerability Database. This product uses the NVD API but is not endorsed or certified by the NVD.
  • New and changed records of the CVE Program, read every 15 minutes, so a rating or fix added after a CVE is published reaches the list, and its alerts, within the hour. CVE content © 1999–2026 The MITRE Corporation, used under the CVE terms of use; CVE® is a registered trademark of The MITRE Corporation.
  • OSV.dev, with the GitHub Advisory Database (CC BY 4.0).
  • WPVulnerability (CC0) for WordPress plugins and themes, and WordPress's own security advisories.
  • Node.js's own security release posts, read every 15 minutes, which name its vulnerabilities the day they are fixed, days before their CVE records.
  • The security advisories projects publish on GitHub, and the CVEs libraries such as Brotli name in their release notes, which also count for the runtimes that bundle them.
  • CISA's Known Exploited Vulnerabilities catalog.

Each day's new ones, grouped, and every critical one as soon as we find it: on the blog.

Run WordPress? The UpHeron plugin alerts you the day one of these affects your own site.