VulnerabilityPublished 7 Oct 2025

CVE-2025-59425: vllm · Covert Timing Channel

Affects vllmSource CVE Database V5

Not known to be exploited · CVSS 7.5 High · fixed in 0.11.0 : patch vllm soon.

Data as of 26 Oct 2026, 17:16 UTC

CVSS 3.1 base score

7.5High

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

EPSS: 0.5% chance of exploitation in 30 days – higher than 46% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.11.0

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: High
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: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
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: 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: 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 7 Oct 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

AI-suggested

European organizations should immediately upgrade all vLLM deployments to version 0.11.0rc2 or later to eliminate the timing attack vulnerability. Where immediate upgrade is not feasible, implement compensating controls such as network-level restrictions to limit access to the API key validation endpoint, and deploy rate limiting to reduce the feasibility of timing analysis attacks. Consider integrating external authentication and authorization mechanisms that do not rely solely on vLLM's built-in API key validation. Employ monitoring and anomaly detection to identify unusual access patterns indicative of timing attacks or brute-force attempts. Developers should audit any custom API key validation code to ensure constant-time comparison methods are used. Additionally, organizations should review and rotate API keys regularly to minimize exposure. Finally, educate security teams about timing attacks and side-channel vulnerabilities to improve detection and response capabilities.

Description

vLLM is an inference and serving engine for large language models (LLMs). Before version 0.11.0rc2, the API key support in vLLM performs validation using a method that was vulnerable to a timing attack. API key validation uses a string comparison that takes longer the more characters the provided API key gets correct. Data analysis across many attempts could allow an attacker to determine when it finds the next correct character in the key sequence. Deployments relying on vLLM's built-in API key validation are vulnerable to authentication bypass using this technique. Version 0.11.0rc2 fixes the issue.

Impact

For European organizations, this vulnerability poses a significant risk to the confidentiality of API keys protecting access to vLLM inference services. Unauthorized access could lead to misuse of AI model inference capabilities, data leakage, or unauthorized query execution. Organizations deploying vLLM in cloud or on-premises environments without additional API key protection mechanisms are particularly vulnerable. The attack requires no privileges or user interaction and can be executed remotely, increasing the threat surface. Given the growing adoption of AI and LLM technologies in sectors such as finance, healthcare, and government across Europe, exploitation could lead to exposure of sensitive data or disruption of AI-powered services. Although integrity and availability are not directly impacted, the breach of authentication could facilitate further attacks or unauthorized data access. The absence of known exploits in the wild provides a window for proactive mitigation, but the high CVSS score underscores the urgency of patching.

CWE-385Covert Timing Channel (opens in a new tab)
Base weaknessLikelihood of exploit: Medium
Covert timing channels convey information by modulating some aspect of system behavior over time, so that the program receiving the information can observe system behavior and infer protected information.
Architecture and Design
Whenever possible, specify implementation strategies that do not introduce time variances in operations.
Implementation
Often one can artificially manipulate the time which operations take or -- when operations occur -- can remove information from the attacker.
Implementation
It is reasonable to add artificial or random delays so that the amount of CPU time consumed is independent of the action being taken by the application.
OWASP Cheat Sheets
Cryptographic Storage (opens in a new tab)
Key Management (opens in a new tab)
OWASP ASVS 4.0.3
V6.2.8 (opens in a new tab)
Attack patterns
Cross-Domain Search Timing (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

Description

AI analysisMachine-generated, updated 7 Oct 2025, 14:30 UTC

WeaknessesCWE-385

Technical details

References

Community reviews

Related threats