Lucene search
+L

747 matches found

Vulnrichment
Vulnrichment
added 2025/05/30 6:38 p.m.14 views

CVE-2025-48944 vLLM Tool Schema allows DoS via Malformed pattern and type Fields

vLLM is an inference and serving engine for large language models LLMs. In version 0.8.0 up to but excluding 0.9.0, 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 ...

6.5CVSS7.1AI score0.00517EPSS
SaveExploits1References2
Vulnrichment
Vulnrichment
added 2025/05/30 6:36 p.m.20 views

CVE-2025-48943 vLLM allows clients to crash the openai server with invalid regex

vLLM is an inference and serving engine for large language models LLMs. Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service ReDoS that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to...

6.5CVSS7.1AI score0.00475EPSS
SaveExploits0References4
CVE
CVE
added 2025/05/30 6:36 p.m.212 views

CVE-2025-48943

The CVE-2025-48943 issue affects vLLM (inference/serving engine). Versions 0.8.0 up to but excluding 0.9.0 are vulnerable to a Denial of Service caused by processing an invalid regex when using structured output; the issue is fixed in 0.9.0. Related Chainguard advisories list affected builds such...

6.5CVSS7AI score0.00475EPSS
SaveExploits0References4Affected Software1
OSV
OSV
added 2025/05/30 6:36 p.m.9 views

CVE-2025-48943 vLLM allows clients to crash the openai server with invalid regex

vLLM is an inference and serving engine for large language models LLMs. Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service ReDoS that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to...

6.5CVSS6.5AI score
SaveExploits0References6
Cvelist
Cvelist
added 2025/05/30 6:36 p.m.55 views

CVE-2025-48943 vLLM allows clients to crash the openai server with invalid regex

vLLM is an inference and serving engine for large language models LLMs. Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service ReDoS that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to...

6.5CVSS0.00475EPSS
SaveExploits0References4
Cvelist
Cvelist
added 2025/05/30 6:33 p.m.53 views

CVE-2025-48942 vLLM DOS: Remotely kill vllm over http with invalid JSON schema

vLLM is an inference and serving engine for large language models LLMs. In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid jsonschema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex...

6.5CVSS0.00538EPSS
SaveExploits1References4
OSV
OSV
added 2025/05/30 6:33 p.m.7 views

CVE-2025-48942 vLLM DOS: Remotely kill vllm over http with invalid JSON schema

vLLM is an inference and serving engine for large language models LLMs. In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid jsonschema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex...

6.5CVSS6.5AI score
SaveExploits0References6
Vulnrichment
Vulnrichment
added 2025/05/30 6:33 p.m.16 views

CVE-2025-48942 vLLM DOS: Remotely kill vllm over http with invalid JSON schema

vLLM is an inference and serving engine for large language models LLMs. In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid jsonschema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex...

6.5CVSS6.3AI score0.00538EPSS
SaveExploits1References4
CVE
CVE
added 2025/05/30 6:33 p.m.200 views

CVE-2025-48942

vLLM is an inference/serving engine for LLMs. CVE-2025-48942 affects versions 0.8.0 up to but excluding 0.9.0; hitting /v1/completions with an invalid json_schema as a Guided Param kills the vLLM server (availability impact). The issue is noted as analogous to CVE-2025-48943 but for a regex inste...

6.5CVSS6.9AI score0.00538EPSS
SaveExploits1References4Affected Software1
OSV
OSV
added 2025/05/30 6:15 p.m.6 views

PYSEC-2025-50

vLLM, an inference and serving engine for large language models LLMs, has a Regular Expression Denial of Service ReDoS vulnerability in the file vllm/entrypoints/openai/toolparsers/pythonictoolparser.py of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and...

6.5CVSS6.6AI score0.00506EPSS
SaveExploits1References6
NVD
NVD
added 2025/05/30 6:15 p.m.19 views

CVE-2025-48887

vLLM, an inference and serving engine for large language models LLMs, has a Regular Expression Denial of Service ReDoS vulnerability in the file vllm/entrypoints/openai/toolparsers/pythonictoolparser.py of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and...

6.5CVSS0.00506EPSS
SaveExploits1References3
Cvelist
Cvelist
added 2025/05/30 5:36 p.m.30 views

CVE-2025-48887 vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

vLLM, an inference and serving engine for large language models LLMs, has a Regular Expression Denial of Service ReDoS vulnerability in the file vllm/entrypoints/openai/toolparsers/pythonictoolparser.py of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and...

6.5CVSS0.00506EPSS
SaveExploits1References3
Vulnrichment
Vulnrichment
added 2025/05/30 5:36 p.m.20 views

CVE-2025-48887 vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

vLLM, an inference and serving engine for large language models LLMs, has a Regular Expression Denial of Service ReDoS vulnerability in the file vllm/entrypoints/openai/toolparsers/pythonictoolparser.py of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and...

6.5CVSS6.4AI score0.00506EPSS
SaveExploits1References3
CVE
CVE
added 2025/05/30 5:36 p.m.200 views

CVE-2025-48887

CVE-2025-48887 affects vLLM command/tool parsing: the ReDoS vulnerability is in vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py for versions 0.6.4 through 0.9.0 (exclusive) . The root cause is a highly complex, nested regex used for tool call detection, enabling catastrophic backtrac...

6.5CVSS6.9AI score0.00506EPSS
SaveExploits1References3Affected Software1
OSV
OSV
added 2025/05/30 5:36 p.m.10 views

CVE-2025-48887 vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`

vLLM, an inference and serving engine for large language models LLMs, has a Regular Expression Denial of Service ReDoS vulnerability in the file vllm/entrypoints/openai/toolparsers/pythonictoolparser.py of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and...

6.5CVSS6.7AI score
SaveExploits0References5
Chainguard
Chainguard
added 2025/05/30 1:15 a.m.8 views

GHSA-9HCF-V7M4-6M2J vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm, py3.10-vllm-cuda-11.8...

5.3AI score
SaveExploits0
Chainguard
Chainguard
added 2025/05/30 1:15 a.m.11 views

GHSA-J828-28RJ-HFHP vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm, py3.10-vllm-cuda-11.8...

5.3AI score
SaveExploits0
Chainguard
Chainguard
added 2025/05/30 1:15 a.m.30 views

CVE-2025-46722 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm, py3.10-vllm-cuda-11.8...

7.3CVSS7.2AI score0.00316EPSS
SaveExploits0
Chainguard
Chainguard
added 2025/05/30 1:15 a.m.9 views

GHSA-4QJH-9FV9-R85R vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm, py3.10-vllm-cuda-11.8...

5.3AI score
SaveExploits0
Chainguard
Chainguard
added 2025/05/30 1:15 a.m.8 views

GHSA-C65P-X677-FGJ6 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm, py3.10-vllm-cuda-11.8...

5.3AI score
SaveExploits0
Rows per page
Query Builder