<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
  <id>https://cve.radiocsirt.org/rss/recent/all/10</id>
  <title>Most recent entries from all</title>
  <updated>2026-11-16T21:16:59.532162+00:00</updated>
  <author>
    <name>Vulnerability-Lookup</name>
    <email>csirt@opendfir.org</email>
  </author>
  <link href="https://cve.radiocsirt.org" rel="alternate"/>
  <generator uri="https://lkiesow.github.io/python-feedgen" version="1.0.0">python-feedgen</generator>
  <subtitle>Contains only the most 10 recent entries.</subtitle>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/euvd-2026-392634</id>
    <title>EUVD-2026-392634</title>
    <updated>2026-11-16T21:16:59.809324+00:00</updated>
    <content>EUVD-2026-392634</content>
    <link href="https://cve.radiocsirt.org/vuln/euvd-2026-392634"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/fkie_cve-2026-115912</id>
    <title>fkie_cve-2026-115912</title>
    <updated>2026-11-16T21:16:59.809361+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
        <p>vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.</p>
      </div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/fkie_cve-2026-115912"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/ghsa-6757-hggm-hp2w</id>
    <title>GHSA-6757-hggm-hp2w — vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled</title>
    <updated>2026-11-16T21:16:59.809433+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> PyPI: vllm</p>
<p>## Affected</p>
<p>- **Ecosystem / package:** pip / `vllm`
- **Affected versions:** vLLM &lt; 0.32.0.</p>
<p>## Summary</p>
<p>When `--mm-processor-cache-type shm` is enabled, vLLM's multimodal SHM cache represents a cached item with an `address` and `monotonic_id` pair and treats that pair as authority to dereference shared memory in the worker. A public scale-out request can supply its own multimodal `features.kwargs_data`, so an authenticated caller can forge an inner SHM carrier that points at attacker-controlled bytes already staged in the ring buffer. The worker then reaches `pickle.loads()` while deserializing the forged object.</p>
<p>This is reachable through ordinary public HTTP routes and does not require `VLLM_ALLOW_INSECURE_SERIALIZATION=1`. The live chain used `/v1/chat/completions/render` to obtain a valid feature envelope, `/v1/chat/completions` to stage attacker-chosen bytes into SHM, and `/inference/v1/generate` to submit the forged inner carrier.</p>
<p>## Affected code</p>
<p>Links pinned to the confirmed commit [`752a3a504485`](https://github.com/vllm-project/vllm/tree/752a3a504485790a2e8491cacbb35c137339ad34) (v0.25.1):</p>
<p>- [`vllm/distributed/device_communicators/shm_object_storage.py#L375-L400`](https://github.com/vllm-project/vllm/blob/752a3a504485790a2e8491cacbb35c137339ad34/vllm/distributed/device_communicators/shm_object_storage.py#L375-L400) — SHM object deserialization reaches `pickle.loads(serialized_data)` for byte objects.
- [`vllm/multimodal/cache.py#L567-L581`](https://github.com/…</p></div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/ghsa-6757-hggm-hp2w"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/pysec-2026-4345</id>
    <title>PYSEC-2026-4345</title>
    <updated>2026-11-16T21:16:59.809557+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml"><p><strong>Affected:</strong> PyPI: vllm</p>
<p>vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-out deployments with shared-memory multimodal caching enabled, workers trust those values and pass attacker-selected bytes to pickle.loads(), allowing arbitrary Python execution even when insecure serialization is disabled. This issue is fixed in version 0.32.0.</p></div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/pysec-2026-4345"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/rhsa-2026:95872</id>
    <title>RHSA-2026:95872 — Red Hat Security Advisory: RHOAI 3.5.3 - Red Hat OpenShift AI</title>
    <updated>2026-11-16T21:16:59.809579+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
        <p>markdown: python-markdown: Denial of Service via inefficient inline link parsing undici: undici: Information disclosure and Denial of Service via malformed Cache-Control directives @fastify/static: @fastify/static: Information disclosure via route guard bypass fast-uri: fast-uri: Host confusion vulnerability via backslash in URI authority undici: undici: Denial of Service via unrequested WebSocket subprotocol extract-zip: extract-zip: Arbitrary file write via symlink in archive encoding/asn1: golang: Go encoding/asn1: Denial of Service via excessive recursion in Unmarshal find-my-way: find-my-way: Denial of Service vulnerability in HTTP/2 server systeminformation: systeminformation: Arbitrary Command Execution via OS Command Injection mlflow: mlflow: Arbitrary file write via FileStore path traversal mcp: mcp: Denial of Service via session memory exhaustion in streamable HTTP servers nltk: NLTK: Information Disclosure via Symlink Sandbox Bypass github.com/klauspost/compress: klauspost/compress: Denial of Service via integer overflow in dictionary processing com.fasterxml.jackson.core/jackson-core: tools.jackson.core/jackson-core: jackson-core: Denial of Service via excessively long JSON property names accelerate: Hugging Face Accelerate: Path Traversal and Denial of Service via weight_map brace-expansion: DoS via unbounded intermediate arrays, bypassing the CVE-2026-14257 mitigation aiohttp: AIOHTTP: HTTP Request Smuggling via WebSocket Upgrade aiohttp: AIOHTTP: Denial of Ser…</p>
      </div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/rhsa-2026:95872"/>
  </entry>
  <entry>
    <id>https://cve.radiocsirt.org/vuln/wid-sec-w-2026-4051</id>
    <title>WID-SEC-W-2026-4051 — vllm: Mehrere Schwachstellen</title>
    <updated>2026-11-16T21:16:59.809886+00:00</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
        <p>Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um beliebigen Programmcode auszuführen, um einen Denial of Service Angriff durchzuführen, um Informationen offenzulegen und um Sicherheitsvorkehrungen zu umgehen.</p>
      </div>
    </content>
    <link href="https://cve.radiocsirt.org/vuln/wid-sec-w-2026-4051"/>
  </entry>
</feed>
