Syntax: kev:true severity:critical epss:>0.95 vendor:cisco patch:false
Filters
Severity
Exploitation
Data Source
Data Quality
Vendor
CWE — Weakness Type
Clear all
Top 20 matches Showing top matches — use filters or a more specific query to narrow
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trust_remote_co
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, hardcoded "trust_remote_code=True" enables HF supply-chain RCE without user opt-in. A
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy's vision-language modu
LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weigh
A vulnerability was found in InternLM LMDeploy up to 0.7.1. It has been classified as critical. Affected is the function load_weight_ckpt of the file lmdeploy/lmdeploy/vl/model/utils.py of the compone
A vulnerability was found in InternLM LMDeploy up to 0.7.1. It has been declared as critical. Affected by this vulnerability is the function Open of the file lmdeploy/docs/en/conf.py. The manipulation
CVE-2026-22807
CRITICAL CVSS 9.8
Find Similar
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolu
CVE-2025-5120
CRITICAL CVSS 10.0
Find Similar
A sandbox escape vulnerability was identified in huggingface/smolagents version 1.14.0, allowing attackers to bypass the restricted execution environment and achieve remote code execution (RCE). The v
CVE-2026-5241
CRITICAL CVSS 9.6
Find Similar
A vulnerability in the LightGlue model loading path of huggingface/transformers version 5.2.0 allows an attacker-controlled model repository to execute arbitrary code during model initialization. The
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when
CVE-2025-45146
CRITICAL CVSS 9.8
Find Similar
ModelCache for LLM through v0.2.0 was discovered to contain an deserialization vulnerability via the component /manager/data_manager.py. This vulnerability allows attackers to execute arbitrary code v
CVE-2025-50472
CRITICAL CVSS 9.8
Find Similar
The modelscope/ms-swift library thru 2.6.1 is vulnerable to arbitrary code execution through deserialization of untrusted data within the `load_model_meta()` function of the `ModelFileSystemCache()` c
A critical remote code execution vulnerability exists in all versions of the HuggingFace transformers library prior to version 5.3.0. The vulnerability allows an attacker to craft a malicious `config.
vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm l
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to a
CVE-2025-32444
CRITICAL CVSS 9.8
Find Similar
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and prior to 0.8.5, having vLLM integration with mooncake, are vulnerable to remote c
A Regular Expression Denial of Service (ReDoS) vulnerability was discovered in the Hugging Face Transformers library, specifically in the `get_imports()` function within `dynamic_module_utils.py`. Thi
The `add_llm` function in `llm_app.py` in infiniflow/ragflow version 0.11.0 contains a remote code execution (RCE) vulnerability. The function uses user-supplied input `req['llm_factory']` and `req['l
StudyMD 0.3.2 contains a persistent cross-site scripting vulnerability that allows attackers to inject malicious scripts into markdown files. Attackers can upload crafted markdown files with embedded
Page 1+ Next →