MediumVulnerabilityLLM-specific

CVE-2026-116178: vLLM denial of service via inconsistent multimodal metadata

Source: NVD(opens in a new tab)
Identifier: CVE-2026-116178
Published: October 25, 2026
Record updated: October 25, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.

Summary

vLLM from 0.20.0 before 0.30.0 contains a denial of service flaw that lets remote attackers crash the engine. Attackers send inconsistent multimodal metadata, such as repeated or overlapping mm_placeholders ranges or mismatched kwargs_data and mm_hashes lists, to the disaggregated /inference/v1/generate endpoint. This produces a negative text span in Qwen2.5-VL position construction that terminates the engine.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 5.9(medium)
CVSS vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
Attack vector: network
Attack complexity: high
Privileges required: none
User interaction: none
EPSS: Not scored. FIRST had not published an EPSS score for this CVE when it was last checked on October 25, 2026.
Disclosure date: October 25, 2026

Weaknesses and techniques

Weakness (CWE): CWE-20

Classification

Attack type: Denial of service
Attack sophistication: Trivial
AI component targeted: Inference
Impact: Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-116178

First tracked: October 25, 2026 at 02:07 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Topics

Inference infrastructure

Summary

Mitigation

Topics

Related items