VulnerabilityPublished 26 Oct 2026Updated 29 Oct 2026

CVE-2026-115917: Vllm · Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with

Affects vllmSource GCVE Database

Compare

Authoritative record:CVE-2026-115917· Low 3.4

Not known to be exploited · CVSS 3.4 Low : upgrade to 0.32.0 when convenient.

Data as of 29 Oct 2026, 14:41 UTC

CVSS 3.1 base score

3.4Low

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

Thin evidence

One scorer or none

CVSS scores by source
CNA (GitHub_M)	CVSS 3.1	3.4

EPSS: 0.2% chance of exploitation in 30 days – higher than 15% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.32.0

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

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

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: High: A successful attack depends on conditions beyond the attacker's control. That is, a successful attack cannot be accomplished at will, but requires the attacker to invest in some measurable amount of effort in preparation or execution against the vulnerable component before a successful attack can be expected. For example, a successful attack may require an attacker to: gather knowledge about the environment in which the vulnerable target/component exists; prepare the target environment to improve exploit reliability; or inject themselves into the logical network path between the target and the resource requested by the victim in order to read and/or modify network communications (e.g., a man in the middle attack).
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: Required: Successful exploitation of this vulnerability requires a user to take some action before the vulnerability can be exploited.
Scope: Changed: An exploited vulnerability can affect resources beyond the security scope managed by the security authority of the vulnerable component. In this case, the vulnerable component and the impacted component are different and managed by different security authorities.
Confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the impacted component.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: None: There is no impact to availability within the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 26 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: 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 29 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.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), 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 0.32.0.

Patches and advisories

Affected software

Product	Affected	Fixed in
PyPIvllm`pkg:pypi/vllm`Other threats	Affected <0.32.0	Fixed in 0.32.0

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

AI-suggested

Upgrade vLLM to version 0.32.0 or later, where the CORSMiddleware configuration no longer allows wildcard origins by default. This official fix addresses the misconfiguration and mitigates the risk. No additional mitigation is required if the upgrade is applied.

Description

vLLM versions prior to 0.32.0 have a misconfiguration in the OpenAI-compatible server where Starlette CORSMiddleware allows all origins by default. This allows a malicious web page to make cross-origin requests from a victim's browser to an unauthenticated vLLM server on localhost, internal networks, or VPNs, potentially consuming GPU resources and reading responses. The vulnerability does not enable cookie-based CSRF attacks as credentials are disabled by default, and bearer token authentication limits exposure to already authorized callers. The issue is fixed in version 0.32.0.

Impact

An attacker can leverage a victim's browser to send cross-origin requests to an unauthenticated vLLM server on localhost or internal networks, potentially consuming GPU resources and reading responses. The vulnerability does not allow cookie-based CSRF attacks due to disabled credentials by default. Deployments with bearer token authentication are only vulnerable if the attacker already possesses a valid token. There is no indication of remote code execution or data exfiltration beyond the described resource consumption and response reading.

References

Community reviews

Loading reviews…