VulnerabilityPublished 8 Jan 2026Updated 11 Sep 2026

CVE-2026-56340: vLLM introduced enhanced protection for CVE-2025-62164

Affects vllmSource GCVE Database

Mentioned vulnerabilities

CVE-2025-62164

Not known to be exploited · CVSS 8.8 High : upgrade to 0.13.0 soon.

Data as of 26 Oct 2026, 17:16 UTC

CVSS 3.1 base score

8.8High

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.6% chance of exploitation in 30 days – higher than 50% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.13.0

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Attack Vector: Network
Attack Complexity: Low
Privileges Required: Low
User Interaction: None
Scope: Unchanged
Confidentiality: High
Integrity: High
Availability: High

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: Low: The attacker is authorized with (i.e., requires) privileges that provide basic user capabilities that could normally affect only settings and files owned by a user. Alternatively, an attacker with Low privileges may have the ability to cause an impact only to non-sensitive resources.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to the impacted component.
Availability: High: There is total loss of availability, resulting in the attacker being able to fully deny access to resources in the impacted component; this loss is either sustained (while the attacker continues to deliver the attack) or persistent (the condition persists even after the attack has completed). Alternatively, the attacker has the ability to deny some availability, but the loss of availability presents a direct, serious consequence to the impacted component (e.g., the attacker cannot disrupt existing connections, but can prevent new connections; the attacker can repeatedly exploit a vulnerability that, in each instance of a successful attack, leaks a only small amount of memory, but after repeated exploitation causes a service to become completely unavailable).

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 8 Jan 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade vllm to 0.13.0.

Affected software

Product	Affected	Fixed in
PyPIvllm	Affected >=0.10.2 <0.13.0	Fixed in 0.13.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Disable the prompt-embeds feature if it is not required. Restrict which users can submit multimodal embedding requests by applying authentication and rate limiting on inference APIs. Upgrade to a fixed vLLM build when it becomes available from Red Hat. The current default disables prompt-embeds, which mitigates the issue, but enabling it without the patch leaves the system vulnerable.

Description

### Summary The fix [here](https://github.com/vllm-project/vllm/pull/27204) for CVE-2025-62164 is not sufficient. The fix only disables prompt embeds by default rather than addressing the root cause, so the DoS vulnerability remains when the feature is enabled. ### Details vLLM's pending change attempts to fix the root cause, which is the missing sparse tensor validation. PyTorch (~v2.0) disables sparse tensor validation (specifically, sparse tensor invariants checks) by default for performance reasons. vLLM is adding the sparse tensor validation to ensure indices are valid, non-negative, and within bounds. These checks help catch malformed tensors. ### PoC NA ### Impact Current fix only added a flag to disable/enable prompt embeds, so by default, prompt embeds feature is disabled in vLLM, which stops DoS attacks through the embeddings. However, It doesn’t address the problem when the flag is enabled and there is still potential for DoS attacks. ### Changes * https://github.com/vllm-project/vllm/pull/30649

Impact

An attacker can remotely cause denial of service by triggering crashes or resource exhaustion through specially crafted embedding requests when prompt-embeds is enabled. There is also potential for out-of-bounds memory corruption, which may lead to arbitrary code execution. The vulnerability affects confidentiality, integrity, and availability of the affected system. Red Hat rates the impact as important for affected versions with prompt-embeds enabled.

Summary

The vulnerability (CVE-2026-56340) in vLLM arises from missing validation of sparse tensor indices in the prompt-embeds feature. PyTorch disables sparse tensor invariant checks by default for performance, and vLLM initially only disabled prompt-embeds by default rather than fixing the root cause. This allows attackers to submit malformed embedding requests that cause denial of service via crashes or resource exhaustion. Additionally, out-of-bounds memory corruption could enable arbitrary code execution. The vendor has introduced a fix that adds sparse tensor validation to ensure indices are valid, non-negative, and within bounds, mitigating the vulnerability. The affected versions are vLLM >=0.10.2 and <0.13.0. Red Hat advisory confirms the vulnerability and recommends disabling prompt-embeds and restricting access until the fixed build is applied.

CWE-123Write-what-where Condition (opens in a new tab)
Base weaknessLikelihood of exploit: High
Any condition where the attacker has the ability to write an arbitrary value to an arbitrary location, often as the result of a buffer overflow.
Architecture and Design · Language Selection
Use a language that provides appropriate memory abstractions.
Operation
Use OS-level preventative functionality integrated after the fact. Not a complete solution.
OWASP Cheat Sheets
XML Security (opens in a new tab)
Mass Assignment (opens in a new tab)
OWASP ASVS 4.0.3
V13.3.1 (opens in a new tab)
V5.1.4 (opens in a new tab)
V5.1.3 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).
CWE-20Improper Input Validation (opens in a new tab)
Class weaknessLikelihood of exploit: HighCWE Top 25 (2025): #18OWASP Top 10 A05:2025: Injection (opens in a new tab)
The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.
MITRE discourages mapping vulnerabilities to this broad entry; the root cause is usually a more specific weakness.
Architecture and Design · Attack Surface Reduction
Consider using language-theoretic security (LangSec) techniques that characterize inputs using a formal language and build "recognizers" for that language. This effectively requires parsing to be a distinct layer that effectively enforces a boundary between raw input and internal data representations, instead of…
Architecture and Design · Libraries or Frameworks
Use an input validation framework such as Struts or the OWASP ESAPI Validation API. Note that using a framework does not automatically address all input validation problems; be mindful of weaknesses that could arise from misusing the framework itself (CWE-1173).
Architecture and Design · Implementation · Attack Surface Reduction
Understand all the potential areas where untrusted inputs can enter the product, including but not limited to: parameters or arguments, cookies, anything read from the network, environment variables, reverse DNS lookups, query results, request headers, URL components, e-mail, files, filenames, databases, and any…
OWASP Cheat Sheets
XML Security (opens in a new tab)
Mass Assignment (opens in a new tab)
Injection Prevention (opens in a new tab)
SQL Injection Prevention (opens in a new tab)
Injection Prevention in Java (opens in a new tab)
OWASP ASVS 4.0.3
V13.3.1 (opens in a new tab)
V5.1.4 (opens in a new tab)
V5.1.3 (opens in a new tab)
Attack patterns
Buffer Overflow via Environment Variables (opens in a new tab)
Server Side Include (SSI) Injection (opens in a new tab)
Cross Zone Scripting (opens in a new tab)
Command Line Execution through SQL Injection (opens in a new tab)
Object Relational Mapping Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).
CWE-502Deserialization of Untrusted Data (opens in a new tab)
Base weaknessLikelihood of exploit: MediumCWE Top 25 (2025): #15OWASP Top 10 A08:2025: Software or Data Integrity Failures (opens in a new tab)
The product deserializes untrusted data without sufficiently ensuring that the resulting data will be valid.
Architecture and Design · Implementation
If available, use the signing/sealing features of the programming language to assure that deserialized data has not been tainted. For example, a hash-based message authentication code (HMAC) could be used to ensure that data has not been modified.
Implementation
When deserializing data, populate a new object rather than just deserializing. The result is that the data flows through safe input validation and that the functions are safe.
Implementation
Explicitly define a final object() to prevent deserialization.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
XML Security (opens in a new tab)
XML External Entity Prevention (opens in a new tab)
Software Supply Chain Security (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.2 (opens in a new tab)
V5.5.3 (opens in a new tab)
V5.5.1 (opens in a new tab)
Attack patterns
Object Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).
CWE-787Out-of-bounds Write (opens in a new tab)
Base weaknessLikelihood of exploit: HighCWE Top 25 (2025): #5
The product writes data past the end, or before the beginning, of the intended buffer.
Requirements · Language Selection
Use a language that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
Architecture and Design · Libraries or Frameworks
Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
Operation · Build and Compilation · Environment Hardening
Use automatic buffer overflow detection mechanisms that are offered by certain compilers or compiler extensions. Examples include: the Microsoft Visual Studio /GS flag, Fedora/Red Hat FORTIFY_SOURCE GCC flag, StackGuard, and ProPolice, which provide various mechanisms including canary-based detection and range/index…
OWASP Cheat Sheets
XML Security (opens in a new tab)
Mass Assignment (opens in a new tab)
OWASP ASVS 4.0.3
V13.3.1 (opens in a new tab)
V5.1.4 (opens in a new tab)
V5.1.3 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 11 Sep 2026, 22:46 UTC

WeaknessesCWE-123, CWE-20, CWE-502 +1

Technical details

References

Community reviews

Related threats