pkg:PyPI/vllm

所有已知漏洞

• CRITICAL10.0CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration
  >= 0.6.5, < 0.8.5
• CRITICAL10.0CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration
  from 0, < a5450f11c95847cf51a17207af9a3ca5ab569b2c | >= 0.6.5, < 0.8.5
• CRITICAL9.8CVE-2026-22778vLLM has RCE In Video Processing
  >= 0.8.3, < 0.14.1
• CRITICAL9.8CVE-2025-47277vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
  >= 0.6.5, < 0.8.5
• CRITICAL9.8CVE-2024-9053vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints
  from 0, <= 0.6.0
• CRITICAL9.8CVE-2024-9053vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints
  from 0, <= 0.6.0
• CRITICAL9.8CVE-2024-9052vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_object
  from 0, <= 0.8.1
• CRITICAL9.8CVE-2024-11041vLLM Deserialization of Untrusted Data vulnerability
  from 0, <= 0.6.2
• CRITICAL9.0CVE-2025-29783vLLM Allows Remote Code Execution via Mooncake Integration
  >= 0.6.5, < 0.8.0
• CRITICAL9.0CVE-2025-29783vLLM Allows Remote Code Execution via Mooncake Integration
  from 0, < 288ca110f68d23909728627d3100e5a8db820aa2 | >= 0.6.5, < 0.8.0
• HIGH8.8CVE-2026-27893vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out
  >= 0.10.1, < 0.18.0
• HIGH8.8CVE-2026-22807vLLM affected by RCE via auto_map dynamic module loading during model initialization
  >= 0.10.1, < 0.14.0
• HIGH8.8CVE-2025-62164vLLM deserialization vulnerability leading to DoS and potential RCE
  >= 0.10.2, < 0.11.1
• HIGH8.8CVE-2025-9141vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder
  >= 0.10.0, < 0.10.1.1
• HIGH8.0CVE-2025-30165Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration
  >= 0.5.2, < 0.10.0
• HIGH7.5CVE-2025-59425vLLM is vulnerable to timing attack at bearer auth
  from 0, < 0.11.0
• HIGH7.5CVE-2025-48956vllm API endpoints vulnerable to Denial of Service Attacks
  >= 0.1.0, < 0.10.1.1
• HIGH7.5CVE-2025-30202Data exposure via ZeroMQ on multi-node vLLM deployment
  >= 0.5.2, < 0.8.5
• HIGH7.5CVE-2025-24357vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator
  from 0, < d3d6bb13fb62da3234addf6574922a4ec0513d04 | from 0, < 0.7.0
• HIGH7.5CVE-2025-24357vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator
  from 0, < 0.7.0
• HIGH7.5CVE-2024-8768vLLM denial of service vulnerability
  from 0, < 0.5.5
• HIGH7.1CVE-2026-24779vLLM vulnerable to Server-Side Request Forgery (SSRF) through MediaConnector
  from 0, < 0.14.1
• HIGH7.1CVE-2025-66448vLLM vulnerable to remote code execution via transformers_utils/get_config
  from 0, < 0.11.1
• HIGH7.1CVE-2025-6242vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class
  >= 0.5.0, < 0.11.0
• MEDIUM6.5CVE-2026-44223vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
  >= 0.18.0, < 0.20.0
• MEDIUM6.5CVE-2026-44223vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
  >= 0.18.0, < 0.20.0
• MEDIUM6.5CVE-2026-44222vLLM Vulnerable to Remote DoS via Special-Token Placeholders
  >= 0.6.1, < 0.20.0
• MEDIUM6.5CVE-2026-34755vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing
  >= 0.7.0, < 0.19.0
• MEDIUM6.5CVE-2026-34755vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing
  >= 0.7.0, < 0.19.0
• MEDIUM6.5CVE-2026-34756vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server
  >= 0.1.0, < 0.19.0
• MEDIUM6.5CVE-2026-22773vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions
  >= 0.6.4, < 0.12.0
• MEDIUM6.5CVE-2026-22773vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions
  >= 0.6.4, < 0.12.0
• MEDIUM6.5CVE-2025-62426vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`
  >= 0.5.5, < 0.11.1
• MEDIUM6.5CVE-2025-62372vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
  >= 0.5.5, < 0.11.1
• MEDIUM6.5CVE-2025-61620vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server
  >= 0.5.1, < 0.11.0
• MEDIUM6.5CVE-2025-48944vLLM Tool Schema allows DoS via Malformed pattern and type Fields
  >= 0.8.0, < 0.9.0
• MEDIUM6.5CVE-2025-48943vLLM allows clients to crash the openai server with invalid regex
  from 0, < 08bf7840780980c7568c573c70a6a8db94fd45ff | >= 0.8.0, < 0.9.0
• MEDIUM6.5CVE-2025-48943vLLM allows clients to crash the openai server with invalid regex
  >= 0.8.0, < 0.9.0
• MEDIUM6.5CVE-2025-48942vLLM DOS: Remotely kill vllm over http with invalid JSON schema
  >= 0.8.0, < 0.9.0
• MEDIUM6.5CVE-2025-48942vLLM DOS: Remotely kill vllm over http with invalid JSON schema
  from 0, < 08bf7840780980c7568c573c70a6a8db94fd45ff | >= 0.8.0, < 0.9.0
• MEDIUM6.5CVE-2025-48887vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
  >= 0.6.4, < 0.9.0
• MEDIUM6.5CVE-2025-48887vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
  from 0, < 4fc1bf813ad80172c1db31264beaef7d93fe0601 | >= 0.6.4, < 0.9.0
• MEDIUM6.5CVE-2025-46560phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service
  >= 0.8.0, < 0.8.5
• MEDIUM6.5CVE-2025-29770vLLM denial of service via outlines unbounded cache on disk
  from 0, < 0.8.0
• MEDIUM6.5CVE-2025-29770vLLM denial of service via outlines unbounded cache on disk
  from 0, < 0.8.0
• MEDIUM6.2CVE-2024-8939vLLM Denial of Service via the best_of parameter
  from 0, <= 0.5.0.post1
• MEDIUM5.6CVE-2026-7141vLLM makes Use of Uninitialized Resource
  from 0, < 0.19.1
• MEDIUM5.4CVE-2026-34753vLLM: Server-Side Request Forgery (SSRF) in `download_bytes_from_url `
  >= 0.16.0, < 0.19.0
• MEDIUM5.4CVE-2026-25960vLLM has SSRF Protection Bypass
  >= 0.15.1, < 0.17.0
• MEDIUM4.2CVE-2025-46722vLLM has a Weakness in MultiModalHasher Image Hashing Implementation
  >= 0.7.0, < 0.9.0
• MEDIUM4.2CVE-2025-46722vLLM has a Weakness in MultiModalHasher Image Hashing Implementation
  from 0, < 99404f53c72965b41558aceb1bc2380875f5d848 | from 0, < 0.9.0
• LOW2.6CVE-2025-46570Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching
  from 0, < 77073c77bc2006eb80ea6d5128f076f5e6c6f54f | from 0, < 0.9.0
• LOW2.6CVE-2025-46570Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching
  from 0, < 0.9.0
• LOW2.6CVE-2025-25183vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
  from 0, < 432117cd1f59c76d97da2eaff55a7d758301dbc7 | from 0, < 0.7.2
• LOW2.6CVE-2025-25183vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
  from 0, < 0.7.2