CVE-2025-46570 vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

CVE-2025-46570 vLLM’s Chunk-Based Prefix Caching Vulnerable to Potential Timing Side-Channel

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

CVE-2025-46570

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

GHSA-HJQ4-87XH-G4FV vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm...

CVE-2025-46722: Improper Validation of Consistency within Input

vLLM is an inference and serving engine for large language models LLMs. In versions starting from 0.7.0 to before 0.9.0, in the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image...

vLLM 安全漏洞

vLLM is a high throughput and memory efficient inference and service engine for LLM from the vLLM open source. A security vulnerability exists in vLLM versions prior to 0.7.0 through 0.9.0, which stems from the use of only raw pixel data without including metadata in the image hash method, which...

CVE-2025-46570: Observable Timing Discrepancy

vLLM is an inference and serving engine for large language models LLMs. Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First Token. These timing differences...

vLLM Tool Schema allows DoS via Malformed pattern and type Fields

Summary The vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference...

GHSA-VRQ3-R879-7M65 vLLM Tool Schema allows DoS via Malformed pattern and type Fields

Summary The vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference...

Uncaught Exception

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Uncaught Exception through the guidedregex parameter when using xgrammar validation. An attacker can cause the application to crash by sending an...

GHSA-9HCF-V7M4-6M2J vLLM allows clients to crash the openai server with invalid regex

Impact A denial of service bug caused the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg, but for regex instead of a JSON schema. Issue with more details: https://github.com/vllm-project/vllm/issues/17313...

vLLM DOS: Remotely kill vllm over http with invalid JSON schema

Summary Hitting the /v1/completions API with a invalid jsonschema as a Guided Param will kill the vllm server Details The following API call venv derekh@ip-172-31-15-108 $ curl -s http://localhost:8000/v1/completions -H "Content-Type: application/json" -d '"model":...

Uncaught Exception

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Uncaught Exception through the guidedjson parameter when using xgrammar validation. An attacker can cause the application to crash by sending an...

GHSA-6QC9-V4R8-22XG vLLM DOS: Remotely kill vllm over http with invalid JSON schema

Summary Hitting the /v1/completions API with a invalid jsonschema as a Guided Param will kill the vllm server Details The following API call venv derekh@ip-172-31-15-108 $ curl -s http://localhost:8000/v1/completions -H "Content-Type: application/json" -d '"model":...

Regular Expression Denial of Service (ReDoS)

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Regular Expression Denial of Service ReDoS in multiple locations in the code. An attacker can cause a denial of service by supplying specially craft...

vLLM vulnerable to Regular Expression Denial of Service

Summary A recent review identified several regular expressions in the vllm codebase that are susceptible to Regular Expression Denial of Service ReDoS attacks. These patterns, if fed with crafted or malicious input, may cause severe performance degradation due to catastrophic backtracking. 1...

GHSA-J828-28RJ-HFHP vLLM vulnerable to Regular Expression Denial of Service

Summary A recent review identified several regular expressions in the vllm codebase that are susceptible to Regular Expression Denial of Service ReDoS attacks. These patterns, if fed with crafted or malicious input, may cause severe performance degradation due to catastrophic backtracking. 1...

Regular Expression Denial of Service (ReDoS)

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Regular Expression Denial of Service ReDoS through the pythonictoolparser.py. An attacker can cause severe performance degradation or make the servi...

GHSA-W6Q7-J642-7C25 vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

Summary A Regular Expression Denial of Service ReDoS vulnerability exists in the file vllm/entrypoints/openai/toolparsers/pythonictoolparser.py of the vLLM project. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an...

vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

Summary A Regular Expression Denial of Service ReDoS vulnerability exists in the file vllm/entrypoints/openai/toolparsers/pythonictoolparser.py of the vLLM project. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an...