CVE Intelligence
Medium Denial of service

CVE-2026-92365 — vllm-project vllm thinking_budget_state.py algorithmic complexity

A vulnerability was found in vllm-project vllm up to 0.29.0. Affected by this issue is some unknown functionality of the file vllm/v1/sample/thinking_budget_state.py. The manipulation results in inefficient algorithmic complexity. It is possible to launch the attack remotely. The pull request to fix this issue awaits acceptance.

Published Sep 16, 2026 · Updated Oct 15, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: VulDB

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • EPSS 0.5% (30-day exploitation probability)+6
  • Technical severity (medium)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
0.52%
ahead of 43% of scored CVEs · Oct 15, 2026
Affects
Vllm-project
Vllm-project/vllm
CVSS base
4.3
Medium · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
None
none · proof-of-concept · active
Automatable
No
can an attacker script the kill-chain steps
Technical impact
Partial
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (Vllm-project Vllm-project/vllm).
  2. No fix documented in the sources: reduce exposure and monitor the vendor advisory.
  3. Search available logs for exploit probes matching the vulnerability class (denial of service), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Vllm-project Vllm-project/vllm version 0.15version 0.29.0version 0.28version 0.27version 0.26version 0.25version 0.24version 0.23
and 21 more version 0.22version 0.21version 0.20version 0.19version 0.18version 0.17version 0.16version 0.1version 0.14version 0.13version 0.12version 0.11version 0.10version 0.9version 0.8version 0.7version 0.6version 0.5version 0.4version 0.3version 0.2
Vulnerable CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
Low
Privileges required
Low
User interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
Low

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
5.3 CVSS 4.0 Medium — — cna@vuldb.com via NIST National Vulnerability Database
5.3 CVSS 4.0 Medium — — VulDB via CVE Program (cve.org) e CISA ADP
4.3 CVSS 3.1 Medium 2.8 1.4 cna@vuldb.com via NIST National Vulnerability Database
4.3 CVSS 3.1 Medium — — VulDB via CVE Program (cve.org) e CISA ADP
4.3 CVSS 3.0 Medium — — VulDB via CVE Program (cve.org) e CISA ADP
4.0 CVSS 2.0 Medium 8.0 2.9 cna@vuldb.com via NIST National Vulnerability Database
4.0 CVSS 2.0 Medium — — VulDB via CVE Program (cve.org) e CISA ADP
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L (score shown at the top: cna@vuldb.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-404 · Improper Resource Shutdown or Release

Other CVEs with this weakness →

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
  • Track CPU/memory spikes and availability drops correlated with request patterns.
web/proxy/WAF logsnetwork IDS/IPSresource metrics

Timeline

What happened to this CVE, newest first.

  • 2026
  • Affected products added · vllm-project/vllm
    Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 15, 2026
  • CVSS changed · 4.3
    Oct 15, 2026 · NIST National Vulnerability Database
  • Source status changed · → Deferred
    Oct 15, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 15, 2026 · NIST National Vulnerability Database
  • CVE published
    Sep 16, 2026 · VulDB

Source activity

Repeated readings are counted rather than listed.

  • 1× Official description updated · Oct 15, 2026 – Oct 15, 2026

References

6 on the record

Elsewhere on this site

Vllm-project
every CVE for this vendor
CWE-404
other pages naming this weakness

Related CVEs (same products)

  • Medium CVE-2026-109311 vLLM before 0.29.0 Heap Overflow DoS via IAMF Audio Transcription Upload 4d
  • Medium CVE-2026-105922 vllm-project vLLM Penalty utils.py get_token_bin_counts_and_mask denial of service 10d
  • Medium CVE-2026-105775 vllm-project vLLM Completions Request mamba_mixer2.py conv_ssm_forward out-of-bounds 10d
  • Medium CVE-2026-105756 vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service 10d
  • High CVE-2026-105759 vLLM: Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens in the vLLM Rust frontend metrics middleware (unauthenticated denial of service) 10d
  • Medium CVE-2026-105758 vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach 10d

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No fixed version, patch or mitigation documented.
  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-92365 is "vllm-project vllm thinking_budget_state.py algorithmic complexity", rated Medium. It affects Vllm-project/vllm (Vllm-project); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 4.3 describes technical severity. EPSS 0.52% estimates the probability of exploitation in 30 days; neither replaces your asset context. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.