vLLM up to 0.8.4 send_obj deserialization

CVSS Meta Temp Score
CVSS is a standardized scoring system to determine possibilities of attacks. The Temp Score considers temporal factors like disclosure, exploit and countermeasures. The unique Meta Score calculates the average score of different sources to provide a normalized scoring system.
Current Exploit Price (≈)
Our analysts are monitoring exploit markets and are in contact with vulnerability brokers. The range indicates the observed or calculated exploit price to be seen on exploit markets. A good indicator to understand the monetary effort required for and the popularity of an attack.
CTI Interest Score
Our Cyber Threat Intelligence team is monitoring different web sites, mailing lists, exploit markets and social media networks. The CTI Interest Score identifies the interest of attackers and the security community for this specific vulnerability in real-time. A high score indicates an elevated risk to be targeted for this vulnerability.
8.4$0-$5k0.00

Summaryinfo

A vulnerability was found in vLLM up to 0.8.4. It has been rated as critical. This vulnerability affects the function send_obj. The manipulation leads to deserialization. This vulnerability is referenced as CVE-2025-47277. Remote exploitation of the attack is possible. No exploit is available. Upgrading the affected component is advised.

Detailsinfo

A vulnerability was found in vLLM up to 0.8.4 and classified as critical. This issue affects the function send_obj. The manipulation with an unknown input leads to a deserialization vulnerability. Using CWE to declare the problem leads to CWE-502. The product deserializes untrusted data without sufficiently verifying that the resulting data will be valid. Impacted is confidentiality, integrity, and availability. The summary by CVE is:

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.

The advisory is shared at github.com. The identification of this vulnerability is CVE-2025-47277 since 05/05/2025. The exploitation is known to be easy. The attack may be initiated remotely. No form of authentication is needed for a successful exploitation. Technical details are known, but no exploit is available.

Upgrading to version 0.8.5 eliminates this vulnerability. Applying the patch 0d6e187e88874c39cda7409cf673f9e6546893e7 is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

The vulnerability is also documented in the vulnerability database at CERT Bund (WID-SEC-2025-2883). Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Affected

  • Red Hat Enterprise Linux

Productinfo

Name

Version

License

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔍
VulDB Reliability: 🔍

CVSSv3info

VulDB Meta Base Score: 8.5
VulDB Meta Temp Score: 8.4

VulDB Base Score: 7.3
VulDB Temp Score: 7.0
VulDB Vector: 🔍
VulDB Reliability: 🔍

CNA Base Score: 9.8
CNA Vector (GitHub_M): 🔍

CVSSv2info

AVACAuCIA
💳💳💳💳💳💳
💳💳💳💳💳💳
💳💳💳💳💳💳
VectorComplexityAuthenticationConfidentialityIntegrityAvailability
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock

VulDB Base Score: 🔍
VulDB Temp Score: 🔍
VulDB Reliability: 🔍

Exploitinginfo

Class: Deserialization
CWE: CWE-502 / CWE-20
CAPEC: 🔍
ATT&CK: 🔍

Physical: No
Local: No
Remote: Yes

Availability: 🔍
Status: Not defined

EPSS Score: 🔍
EPSS Percentile: 🔍

Price Prediction: 🔍
Current Price Estimation: 🔍

0-DayUnlockUnlockUnlockUnlock
TodayUnlockUnlockUnlockUnlock

Threat Intelligenceinfo

Interest: 🔍
Active Actors: 🔍
Active APT Groups: 🔍

Countermeasuresinfo

Recommended: Upgrade
Status: 🔍

0-Day Time: 🔍

Upgrade: vLLM 0.8.5
Patch: 0d6e187e88874c39cda7409cf673f9e6546893e7

Timelineinfo

05/05/2025 🔍
05/20/2025 +15 days 🔍
05/20/2025 +0 days 🔍
12/20/2025 +214 days 🔍

Sourcesinfo

Advisory: GHSA-hjq4-87xh-g4fv
Status: Confirmed

CVE: CVE-2025-47277 (🔍)
GCVE (CVE): GCVE-0-2025-47277
GCVE (VulDB): GCVE-100-309785
CERT Bund: WID-SEC-2025-2883 - Red Hat Enterprise AI Inference Server (vLLM): Schwachstelle ermöglicht Codeausführung

Entryinfo

Created: 05/20/2025 20:25
Updated: 12/20/2025 06:41
Changes: 05/20/2025 20:25 (65), 08/14/2025 05:22 (1), 12/20/2025 06:41 (7)
Complete: 🔍
Cache ID: 216::103

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion

No comments yet. Languages: en.

Please log in to comment.

Interested in the pricing of exploits?

See the underground prices here!