4180 matches found
CVE-2025-59425: Covert Timing Channel
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 A...
vLLM security vulnerabilities
vLLM is a vLLM open source high throughput and memory efficient inference and service engine for LLM. A security vulnerability exists in versions prior to vLLM 0.11.0rc2, which stems from a timing attack vulnerability in the API key authentication method that could lead to authentication bypass...
EUVD-2024-0655
Malicious code in bioql PyPI...
EUVD-2023-0895
Malicious code in bioql PyPI...
EUVD-2023-1119
Malicious code in bioql PyPI...
EUVD-2024-0067
Malicious code in bioql PyPI...
EUVD-2023-1438
Malicious code in bioql PyPI...
EUVD-2022-0830
Malicious code in bioql PyPI...
EUVD-2022-48288
Malicious code in bioql PyPI...
EUVD-2022-2493
Malicious code in bioql PyPI...
EUVD-2022-28752
Malicious code in bioql PyPI...
EUVD-2024-2694
Malicious code in bioql PyPI...
EUVD-2023-2645
Malicious code in bioql PyPI...
EUVD-2021-29004
Malicious code in bioql PyPI...
EUVD-2021-30241
Malicious code in bioql PyPI...
EUVD-2022-6368
Malicious code in bioql PyPI...
EUVD-2022-5095
Malicious code in bioql PyPI...
EUVD-2024-2648
Malicious code in bioql PyPI...