VulnerabilityPublished 21 Nov 2025Updated 24 Nov 2025

CVE-2025-62426: vllm · Unthrottled Resource Allocation

Affects vllmSource CVE Database V5

Not known to be exploited · CVSS 6.5 Medium : upgrade to 0.11.1 when convenient.

Data as of 26 Oct 2026, 15:59 UTC

CVSS 3.1 base score

6.5Medium

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

EPSS: 0.5% chance of exploitation in 30 days – higher than 45% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.11.1

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: Low
User Interaction: None
Scope: Unchanged
Confidentiality: None
Integrity: None
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: None: There is no loss of confidentiality within the impacted component.
Integrity: None: There is no loss of integrity within 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 21 Nov 2025
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-project/vllm to 0.11.1.

Affected software

Product	Affected	Fixed in
GitHubvllm-project/vllm`pkg:github/vllm-project/vllm`Other threats	Affected <0.11.1 >=0.5.5	Fixed in 0.11.1

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

AI-suggested

To mitigate this vulnerability, European organizations should promptly upgrade all vllm deployments to version 0.11.1 or later, where the issue is patched. Implement strict input validation and sanitization for the chat_template_kwargs parameter to prevent malformed or malicious payloads from triggering resource exhaustion. Deploy rate limiting and throttling mechanisms on the affected API endpoints (/v1/chat/completions and /tokenize) to limit the impact of any single client or request. Monitor API usage patterns for anomalies indicative of exploitation attempts, such as unusually long processing times or repeated requests with suspicious parameters. Restrict access to the API endpoints to trusted users and systems, enforcing strong authentication and authorization controls. Employ network segmentation and firewall rules to limit exposure of the inference engine to only necessary clients. Regularly audit and review logs for signs of abuse or performance degradation. Finally, maintain an incident response plan that includes procedures for mitigating denial of service conditions affecting AI services.

Description

vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

Impact

For European organizations, this vulnerability poses a significant risk to the availability of AI inference services relying on the vllm engine. Organizations using affected versions may experience denial of service conditions, leading to service outages or degraded performance of LLM-based applications. This can disrupt business operations, especially in sectors such as finance, healthcare, research, and technology where AI-driven services are increasingly critical. The inability to process API requests timely could impact customer-facing applications, internal automation, and decision-making systems. Additionally, prolonged service disruptions could lead to reputational damage and financial losses. Since the vulnerability requires privileged access to the API, insider threats or compromised credentials could be leveraged to exploit this issue. The lack of impact on confidentiality and integrity limits data breach risks, but availability impacts alone can have severe operational consequences. European organizations with strict service-level agreements (SLAs) and regulatory requirements for uptime may face compliance challenges if affected.

CWE-770Allocation of Resources Without Limits or Throttling (opens in a new tab)
Base weaknessLikelihood of exploit: HighCWE Top 25 (2025): #25
The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.
Requirements
Clearly specify the minimum and maximum expectations for capabilities, and dictate which behaviors are acceptable when resource allocation reaches limits.
Architecture and Design
Limit the amount of resources that are accessible to unprivileged users. Set per-user limits for resources. Allow the system administrator to define these limits. Be careful to avoid CWE-410.
Architecture and Design
Design throttling mechanisms into the system architecture. The best protection is to limit the amount of resources that an unauthorized user can cause to be expended.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
OWASP ASVS 4.0.3
V8.1.4 (opens in a new tab)
V13.4.1 (opens in a new tab)
V11.1.4 (opens in a new tab)
Attack patterns
XML Ping of the Death (opens in a new tab)
Exponential Data Expansion (opens in a new tab)
Serialized Data Parameter Blowup (opens in a new tab)
Serialized Data with Nested Payloads (opens in a new tab)
Oversized Serialized Data Payloads (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 28 Nov 2025, 04:41 UTC

WeaknessesCWE-770

Technical details

References

Community reviews

Related threats