Moonshot AI Kimi Code up to 0.31.0 MCP Configuration Loader config-loader.ts os command injection

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.
5.7$0-$5k1.25

Summaryinfo

A vulnerability was found in Moonshot AI Kimi Code up to 0.31.0. It has been rated as critical. The impacted element is an unknown function of the file agent-core-v2/src/agent/mcp/config-loader.ts of the component MCP Configuration Loader. This manipulation causes os command injection. This vulnerability is registered as CVE-2026-95660. Remote exploitation of the attack is possible. Furthermore, an exploit is available. Upgrading the affected component is advised. Beyond the trust prompt, the fix resolves fd/stty binaries to absolute paths specifically "so untrusted workspaces cannot plant bare-name executables before confirmation," fixing a secondary $PATH path-planting vector alongside the primary untrusted-.mcp.json auto-spawn.

Detailsinfo

A vulnerability has been found in Moonshot AI Kimi Code up to 0.31.0 and classified as critical. Affected by this vulnerability is an unknown function of the file agent-core-v2/src/agent/mcp/config-loader.ts of the component MCP Configuration Loader. The manipulation with an unknown input leads to a os command injection vulnerability. The CWE definition for the vulnerability is CWE-78. The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component. As an impact it is known to affect confidentiality, integrity, and availability.

It is possible to read the advisory at docs.google.com. This vulnerability is known as CVE-2026-95660. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. It demands that the victim is doing some kind of user interaction. Technical details and also a public exploit are known. The attack technique deployed by this issue is T1202 according to MITRE ATT&CK.

It is possible to download the exploit at docs.google.com. It is declared as proof-of-concept. Beyond the trust prompt, the fix resolves fd/stty binaries to absolute paths specifically "so untrusted workspaces cannot plant bare-name executables before confirmation," fixing a secondary $PATH path-planting vector alongside the primary untrusted-.mcp.json auto-spawn.

Upgrading to version 0.31.1 eliminates this vulnerability. The upgrade is hosted for download at github.com.

Be aware that VulDB is the high quality source for vulnerability data.

Productinfo

Type

Vendor

Name

Version

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔒
VulDB Reliability: 🔍

CVSSv3info

VulDB Meta Base Score: 6.3
VulDB Meta Temp Score: 5.7

VulDB Base Score: 6.3
VulDB Temp Score: 5.7
VulDB Vector: 🔒
VulDB Reliability: 🔍

CVSSv2info

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

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

Exploitinginfo

Class: Os command injection
CWE: CWE-78 / CWE-77 / CWE-74
CAPEC: 🔒
ATT&CK: 🔒

Physical: No
Local: No
Remote: Yes

Availability: 🔒
Access: Public
Status: Proof-of-Concept
Download: 🔒
Price Prediction: 🔍
Current Price Estimation: 🔒

0-DayUnlockUnlockUnlockUnlock
TodayUnlockUnlockUnlockUnlock

Threat Intelligenceinfo

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

Countermeasuresinfo

Recommended: Upgrade
Status: 🔍

0-Day Time: 🔒

Upgrade: Kimi Code 0.31.1

Timelineinfo

09/22/2026 Advisory disclosed
09/22/2026 +0 days VulDB entry created
09/22/2026 +0 days VulDB entry last update

Sourcesinfo

Advisory: docs.google.com
Status: Confirmed

CVE: CVE-2026-95660 (🔒)
GCVE (CVE): GCVE-0-2026-95660
GCVE (VulDB): GCVE-100-408415
scip Labs: https://www.scip.ch/en/?labs.20161013

Entryinfo

Created: 09/22/2026 14:47
Changes: 09/22/2026 14:47 (59)
Complete: 🔍
Submitter: 38.5
Cache ID: 216::103

Submitinfo

Accepted

Be aware that VulDB is the high quality source for vulnerability data.

Discussion

No comments yet. Languages: en.

Please log in to comment.

Might our Artificial Intelligence support you?

Check our Alexa App!