<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Most recent entries from all</title>
    <link>https://cve.radiocsirt.org</link>
    <description>Contains only the most 10 recent entries.</description>
    <docs>http://www.rssboard.org/rss-specification</docs>
    <generator>python-feedgen</generator>
    <language>en</language>
    <lastBuildDate>Fri, 02 Oct 2026 18:39:51 +0000</lastBuildDate>
    <item>
      <title>EUVD-2026-333537</title>
      <link>https://cve.radiocsirt.org/vuln/euvd-2026-333537</link>
      <description>EUVD-2026-333537</description>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/euvd-2026-333537</guid>
    </item>
    <item>
      <title>fkie_cve-2026-55574</title>
      <link>https://cve.radiocsirt.org/vuln/fkie_cve-2026-55574</link>
      <description>&lt;p&gt;vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/fkie_cve-2026-55574</guid>
    </item>
    <item>
      <title>GHSA-rwxx-mrjm-wc2m — vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-rwxx-mrjm-wc2m</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: vllm&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;The `structured_outputs.regex` API parameter passes a user-supplied regex string directly to grammar compiler backends with no compilation timeout. In the xgrammar backend, the string reaches `compile_regex()` with no guard. In the outlines backend, `validate_regex_is_buildable()` blocks structural issues (lookarounds, backreferences) but provides zero protection against exponential DFA state-space explosion. Patterns like `(a+)+b` pass all checks and hang the inference worker.&lt;/p&gt;
&lt;p&gt;## Root Cause&lt;/p&gt;
&lt;p&gt;`backend_xgrammar.py:91` — no timeout:
```python
ctx = self.compiler.compile_regex(grammar_spec)
```&lt;/p&gt;
&lt;p&gt;`backend_outlines.py:299–330` — structural checks only, no complexity analysis:
```python
def validate_regex_is_buildable(regex: str) -&amp;gt; None:
    sre_parse.parse(regex)   # AST parse only — does not detect exponential patterns
    _check_unsupported(...)  # blocks lookarounds/backrefs, not nested quantifiers
```&lt;/p&gt;
&lt;p&gt;`backend_outlines.py:64` — no timeout:
```python
oc.Index(regex_string, vocabulary.inner)
```&lt;/p&gt;
&lt;p&gt;## Impact&lt;/p&gt;
&lt;p&gt;Denial of service — one request with an adversarial regex pattern hangs an inference worker indefinitely.&lt;/p&gt;
&lt;p&gt;## Remediation&lt;/p&gt;
&lt;p&gt;Wrap `compile_regex()` and `oc.Index()` calls in a thread with a deadline (e.g., 5 seconds). Add complexity analysis to `validate_regex_is_buildable()` to detect nested quantifier patterns before compilation.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: vllm&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;The `structured_outputs.regex` API parameter passes a user-supplied regex string directly to grammar compiler backends with no compilation timeout. In the xgrammar backend, the string reaches `compile_regex()` with no guard. In the outlines backend, `validate_regex_is_buildable()` blocks structural issues (lookarounds, backreferences) but provides zero protection against exponential DFA state-space explosion. Patterns like `(a+)+b` pass all checks and hang the inference worker.&lt;/p&gt;
&lt;p&gt;## Root Cause&lt;/p&gt;
&lt;p&gt;`backend_xgrammar.py:91` — no timeout:
```python
ctx = self.compiler.compile_regex(grammar_spec)
```&lt;/p&gt;
&lt;p&gt;`backend_outlines.py:299–330` — structural checks only, no complexity analysis:
```python
def validate_regex_is_buildable(regex: str) -&amp;gt; None:
    sre_parse.parse(regex)   # AST parse only — does not detect exponential patterns
    _check_unsupported(...)  # blocks lookarounds/backrefs, not nested quantifiers
```&lt;/p&gt;
&lt;p&gt;`backend_outlines.py:64` — no timeout:
```python
oc.Index(regex_string, vocabulary.inner)
```&lt;/p&gt;
&lt;p&gt;## Impact&lt;/p&gt;
&lt;p&gt;Denial of service — one request with an adversarial regex pattern hangs an inference worker indefinitely.&lt;/p&gt;
&lt;p&gt;## Remediation&lt;/p&gt;
&lt;p&gt;Wrap `compile_regex()` and `oc.Index()` calls in a thread with a deadline (e.g., 5 seconds). Add complexity analysis to `validate_regex_is_buildable()` to detect nested quantifier patterns before compilation.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-rwxx-mrjm-wc2m</guid>
    </item>
    <item>
      <title>PYSEC-2026-2304</title>
      <link>https://cve.radiocsirt.org/vuln/pysec-2026-2304</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: vllm&lt;/p&gt;
&lt;p&gt;vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: vllm&lt;/p&gt;
&lt;p&gt;vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex compiler with no guard, and in the outlines backend the validation step blocks structural issues such as lookarounds and backreferences but performs no complexity analysis, so a pattern with nested quantifiers passes all checks and causes exponential state-space expansion, allowing a single request containing an adversarial regex to hang an inference worker indefinitely and deny service. This issue is fixed in version 0.24.0.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/pysec-2026-2304</guid>
    </item>
    <item>
      <title>RHSA-2026:60363 — Red Hat Security Advisory: Red Hat AI Inference Server 3.3.6 (Spyre)</title>
      <link>https://cve.radiocsirt.org/vuln/rhsa-2026:60363</link>
      <description>&lt;p&gt;vllm: vLLM: Denial of Service via malformed multimodal input or token injection vllm: vLLM: Supply-chain integrity issue due to inconsistent revision pinning controls vllm: vLLM: Information disclosure via integer truncation vllm: vLLM: Denial of Service via malformed speculative decoding workload vllm: vLLM: Denial of Service via adversarial regular expression in structured outputs API&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;vllm: vLLM: Denial of Service via malformed multimodal input or token injection vllm: vLLM: Supply-chain integrity issue due to inconsistent revision pinning controls vllm: vLLM: Information disclosure via integer truncation vllm: vLLM: Denial of Service via malformed speculative decoding workload vllm: vLLM: Denial of Service via adversarial regular expression in structured outputs API&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/rhsa-2026:60363</guid>
    </item>
    <item>
      <title>WID-SEC-W-2026-2176 — vllm: Mehrere Schwachstellen ermöglichen Denial of Service</title>
      <link>https://cve.radiocsirt.org/vuln/wid-sec-w-2026-2176</link>
      <description>&lt;p&gt;Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;Ein Angreifer kann mehrere Schwachstellen in vllm ausnutzen, um einen Denial of Service Angriff durchzuführen.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/wid-sec-w-2026-2176</guid>
    </item>
  </channel>
</rss>
