EUVD-2025-19433

| CVE-2025-53098 HIGH
2025-06-27 [email protected]
8.1
CVSS 3.1
Share

CVSS Vector

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack Vector
Network
Attack Complexity
High
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Lifecycle Timeline

4
Analysis Generated
Mar 16, 2026 - 00:16 vuln.today
EUVD ID Assigned
Mar 16, 2026 - 00:16 euvd
EUVD-2025-19433
Patch Released
Mar 16, 2026 - 00:16 nvd
Patch available
CVE Published
Jun 27, 2025 - 22:15 nvd
HIGH 8.1

Description

Roo Code is an AI-powered autonomous coding agent. The project-specific MCP configuration for the Roo Code agent is stored in the `.roo/mcp.json` file within the VS Code workspace. Because the MCP configuration format allows for execution of arbitrary commands, prior to version 3.20.3, it would have been possible for an attacker with access to craft a prompt to ask the agent to write a malicious command to the MCP configuration file. If the user had opted-in to auto-approving file writes within the project, this would have led to arbitrary command execution. This issue is of moderate severity, since it requires the attacker to already be able to submit prompts to the agent (for instance through a prompt injection attack), for the user to have MCP enabled (on by default), and for the user to have enabled auto-approved file writes (off by default). Version 3.20.3 fixes the issue by adding an additional layer of opt-in configuration for auto-approving writing to Roo's configuration files, including all files within the `.roo/` folder.

Analysis

Roo Code is an AI-powered autonomous coding agent. The project-specific MCP configuration for the Roo Code agent is stored in the .roo/mcp.json file within the VS Code workspace. Because the MCP configuration format allows for execution of arbitrary commands, prior to version 3.20.3, it would have been possible for an attacker with access to craft a prompt to ask the agent to write a malicious command to the MCP configuration file. If the user had opted-in to auto-approving file writes within the project, this would have led to arbitrary command execution. This issue is of moderate severity, since it requires the attacker to already be able to submit prompts to the agent (for instance through a prompt injection attack), for the user to have MCP enabled (on by default), and for the user to have enabled auto-approved file writes (off by default). Version 3.20.3 fixes the issue by adding an additional layer of opt-in configuration for auto-approving writing to Roo's configuration files, including all files within the .roo/ folder.

Technical Context

Command injection allows an attacker to execute arbitrary OS commands on the host system through a vulnerable application that passes user input to system shells.

Affected Products

Affected products: Roocode Roo Code

Remediation

A vendor patch is available — apply it immediately. Avoid passing user input to system commands. Use language-specific APIs instead of shell commands. If unavoidable, use strict input validation and escaping.

Priority Score

41
Low Medium High Critical
KEV: 0
EPSS: +0.1
CVSS: +40
POC: 0

Share

EUVD-2025-19433 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy