CVE Intelligence
High Input validation

CVE-2026-56340 — vLLM - Denial of Service via Unvalidated Multimodal Embeddings

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

Published Jun 20, 2026 · Updated Oct 13, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: VulnCheck

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 0.6% (30-day exploitation probability)+7
  • Technical severity (high)+6

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
0.64%
ahead of 50% of scored CVEs · Oct 14, 2026
Affects
Vllm
Vllm
CVSS base
7.5
High · 4 source(s)
Prioritization reference: 8.8 provisional

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
Total
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 Vllm).
  2. The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
  3. No fix documented in the sources: reduce exposure and monitor the vendor advisory.
  4. Search available logs for exploit probes matching the vulnerability class (input validation), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
Vllm Vllm ≥ 0.10.2 and < 0.13.0 Vulnerable NIST National Vulnerability Database
Vllm Vllm ≥ 0.10.2 and < 0.13.0 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
None
User interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
None
Availability
High

Every base score collected

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

ScoreVersionSeverityExpl.ImpactScored by
8.7 CVSS 4.0 High — — disclosure@vulncheck.com via NIST National Vulnerability Database
8.7 CVSS 4.0 High — — VulnCheck via CVE Program (cve.org) e CISA ADP
8.8 CVSS 3.1 High 2.8 5.9 disclosure@vulncheck.com via NIST National Vulnerability Database
8.8 CVSS 3.1 High 2.8 5.9 0b0ca135-0b70-47e7-9f44-1890c2a1c46c via NIST National Vulnerability Database
8.8 CVSS 3.1 High — — VulnCheck via CVE Program (cve.org) e CISA ADP
7.5 CVSS 3.1 High 3.9 3.6 nvd@nist.gov via NIST National Vulnerability Database
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H (score shown at the top: nvd@nist.gov)
Scoring entities (NIST, CNA, ADP) score independently; each score is shown with its origin. For prioritization we use 8.8 (disclosure@vulncheck.com via NIST National Vulnerability Database) as a conservative provisional reference — not a definitive official score.

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-20 · Improper Input Validation

Other CVEs with this weakness →

EPSS over time FIRST

Oct 13, 2026 → Oct 14, 2026 · 2 reading(s) · max 0.64%

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).
web/proxy/WAF logsnetwork IDS/IPS

Timeline

What happened to this CVE, newest first.

  • 2026
  • Affected products added · vllm/vllm
    Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 13, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 13, 2026
  • CVSS changed · 7.5
    Oct 13, 2026 · NIST National Vulnerability Database
  • Source status changed · → Modified
    Oct 13, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 13, 2026 · NIST National Vulnerability Database
  • CVE published
    Jun 20, 2026 · VulnCheck

Source activity

Repeated readings are counted rather than listed.

  • 1× Official description updated · Oct 13, 2026 – Oct 13, 2026

References

5 on the record

Elsewhere on this site

Vllm
every CVE for this vendor
Input validation
same class
CWE-20
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-105922 vllm-project vLLM Penalty utils.py get_token_bin_counts_and_mask denial of service 9d
  • 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
  • CVE-2026-105754 vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features 10d
  • CVE-2026-105755 vLLM: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank` 10d
  • CVE-2026-105757 vLLM: Structured-output request errors escape the request boundary and terminate the shared EngineCore — engine-fatal denial of service (3 sites) 10d
  • 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

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-2026-56340 is "vLLM - Denial of Service via Unvalidated Multimodal Embeddings", rated High. It affects Vllm (Vllm); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 7.5 describes technical severity. EPSS 0.64% 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.