Vllm
CVE-2025-47277
CRITICAL
GHSA-hjq4-87xh-g4fv
Vulnerability Assessment
| Weakness |
CWE
OWASP Top 10:2025
A08:2025 - Software or Data Integrity Failures
ASVS 5.0
V1 - Encoding and Sanitization Safe deserialization, type allowlists
MITRE ATT&CK
2 techniques across 2 tactics: Execution, Initial Access The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up. |
| Impact | CVSS score of 9.8 (CRITICAL). Attack characteristics: network attack vector, low complexity, no privileges required, no user interaction not required. Public proof-of-concept exploit code is available. EPSS exploitation probability: 0.86%. |
| Exploit ScenarioDerived | A remote attacker could execute arbitrary code through malicious serialized objects by sending crafted requests to the affected application. No authentication is required to exploit this vulnerability. |
Get an e-mail when this CVE is exploited, patched or re-scored. Free account.
Alert meAnalysisAIv1 – Mar 28, 2026
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the PyNcclPipe KV cache transfer. Rated critical severity (CVSS 9.8), this vulnerability is remotely exploitable, no authentication required, low attack complexity. Public exploit code available.
RemediationAI
A vendor patch is available. Apply the latest security update as soon as possible. Avoid deserializing untrusted data. Use safe serialization formats (JSON). Implement integrity checks and type allowlists.
Affected Packages
Source: OSV (Open Source Vulnerabilities)
Affects your stack
Affects 1 package in pypi
Checking this CVE against your own stacks and servers is part of the Basic plan and up.
Technical ContextAI · show details
This vulnerability is classified as Deserialization of Untrusted Data (CWE-502), which allows attackers to execute arbitrary code through malicious serialized objects. vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the PyNcclPipe KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the PyNcclPipe class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the PyNcclCommunicator class, while CPU-side control message passing is handled via the send_obj and recv_obj methods on the CPU side. The intention was that this interface should only be exposed to a private network using the IP address specified by the --kv-ip CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the TCPStore interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the TCPStore instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the TCPStore socket to the private interface as configured. Affected products include: Vllm. Version information: through 0.8.4.
Know when Vllm gets its next vulnerability
- Watch products and get an email when something new is published
- Check this CVE against your own stack and servers
- Exploit and PoC references, threat intelligence from 22 sources
No credit card · 7-day full trial
Severity by source
Sources disagree (Medium–Critical)AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
vuln.today treats the vendor’s rating as authoritative. A higher third-party CVSS (e.g. CISA-ADP) is shown for transparency but does not drive the headline severity.
CVSS VectorGitHub Advisory
Lifecycle Timeline
3DescriptionGitHub Advisory
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the PyNcclPipe KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the PyNcclPipe class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the PyNcclCommunicator class, while CPU-side control message passing is handled via the send_obj and recv_obj methods on the CPU side. The intention was that this interface should only be exposed to a private network using the IP address specified by the --kv-ip CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the TCPStore interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the TCPStore instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the TCPStore socket to the private interface as configured.
Executive ViewAI
Organizations using versions 0.6.5 face critical risk from CVE-2025-47277, a insecure deserialization vulnerability rated CVSS 9.8. Insecure deserialization could allow attackers to execute arbitrary code by providing crafted serialized data. Proof-of-concept code is publicly available, increasing the risk of exploitation. A patch is available and should be applied immediately given the critical severity.
Apply vendor patch. If immediate patching is not feasible: (1) Restrict deserialization endpoints; (2) Implement integrity checks on serialized data; (3) Use type-safe alternatives.
Threat Intelligence Overview
How this decision was reached
The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.
What every action level means
SSVC AssessmentENISA
Priority Score
Attack Technique
Insecure deserialization occurs when an application converts serialized data (a stream of bytes representing an object's state) back into a living object without proper validation.
Affected Products (CPE)GitHub Advisory
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Rated critical severity (CVSS 10.0
vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. Rated critical sev
Information exposure in vLLM inference engine versions 0.8.3 to before 0.14.1. Invalid image requests to the multimodal
Timing-based API key recovery in vLLM before 0.11.0rc2 can let remote attackers bypass bearer-token authentication on de
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Rated high severity (CVSS 7.5), th
Denial of service in the vLLM LLM inference server (all versions prior to 0.24.0) allows a remote client to crash the sh
vLLM before version 0.14.1 contains a server-side request forgery vulnerability in the MediaConnector class where incons
Out-of-memory worker crashes in vLLM can be induced by a single small compressed audio payload submitted to the /v1/chat
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Rated medium severity (CVSS 6.5),
GPU memory exhaustion in vLLM versions prior to 0.28.0 lets an attacker with low-privileged API access (PR:L in the CVSS
Multimodal inference requests to vLLM deployments running versions prior to 0.28.0 can trigger a process-level assertion
Uncontrolled resource consumption in vLLM's OpenAI-compatible completions endpoint allows any authenticated API client t
Exploit-DB