Cyber Resilience

CVE-2025-53098

HighRCE

Published: 27 June 2025

Published
27 June 2025
Modified
15 September 2025
KEV Added
Patch
CVSS Score v3.1 8.1 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS Score 0.0037 59.6th percentile
Risk Priority 16 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-53098 is a high-severity Command Injection (CWE-77) vulnerability in Roocode Roo Code. Its CVSS base score is 8.1 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Client Execution (T1203); ranked in the top 40.4% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain; MITRE ATLAS techniques in scope: LLM Prompt Injection (AML.T0051), AI Agent Context Poisoning (AML.T0080).

EU & UK References

Vulnerability details

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…

more

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.

CWE(s)

AI Security AnalysisAI

AI Category
AI Agent Protocols and Integrations
Risk Domain
Protocol-Specific Risks
OWASP Top 10 for LLMs 2025
LLM01:2025 Prompt Injection
Classification Reason
Matched keywords: ai, mcp, prompt injection

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1203 Exploitation for Client Execution Execution
Adversaries may exploit software vulnerabilities in client applications to execute code.
T1059 Command and Scripting Interpreter Execution
Adversaries may abuse command and script interpreters to execute commands, scripts, or binaries.
Why these techniques?

Vulnerability allows prompt injection to write malicious commands to MCP config file, enabling arbitrary command execution via client software exploitation (T1203) and command interpreter abuse (T1059).

MITRE ATLAS TechniquesAI

MITRE ATLAS techniques

AML.T0051: LLM Prompt InjectionAML.T0080: AI Agent Context Poisoning

Affected Assets

roocode
roo code
≤ 3.20.3

Mitigating Controls

No mitigating controls mapped yet. The per-CVE control annotator has not reached this CVE.

References