CVE-2025-59425
Vllm ≤ 0.11.0
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:NSummary
CVE-2025-59425 is a high-severity Covert Timing Channel (CWE-385) vulnerability in Vllm Vllm. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Data Obfuscation (T1001); ranked at the 42th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as NLP and Transformers; in the Other ATLAS/OWASP Terms risk domain.
The strongest mitigations our analysis identified map to SC-31 (Covert Channel Analysis) — see the control section below for these in your framework.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-32058
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- NLP and Transformers
- Risk Domain
- Other ATLAS/OWASP Terms
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: llms, vllm
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Covert channel analysis directly identifies timing channels that could leak information.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure development practices (reviews, testing) directly reduce introduction of timing-channel vulnerabilities in code.
Runtime monitoring of hardware/software behavior can detect anomalous timing patterns that indicate covert channels.
Vulnerability identification processes can surface timing-channel weaknesses during design or code analysis.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Detailed logging can reveal timing anomalies but does not prevent covert timing channels.
Continuous monitoring may detect timing-based exfiltration but does not eliminate the channel itself.
Network segmentation reduces attack surface but does not address intra-process timing channels.
Network segregation limits external timing observation but not internal covert timing.
Secure architecture principles can include timing-channel countermeasures but are not specific.
Secure coding guidelines may recommend constant-time algorithms but coverage is not guaranteed.