What is the CVSS score of CVE-2025-58370?

CVE-2025-58370 has a CVSS 3.1 base score of 8.1 (High). CVSS vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.1%.

Which versions of Roo Code are affected by CVE-2025-58370?

Organizations using Roo Code face notable risk from CVE-2025-58370, a OS command injection vulnerability rated CVSS 8.1.

How to fix or mitigate CVE-2025-58370?

Within 30 days: Identify all affected systems and apply vendor patches as part of regular patch cycle. Validate that input sanitization is in place for all user-controlled parameters.

Roo Code CVE-2025-58370

HIGH

OS Command Injection (CWE-78)

2025-09-05 security-advisories@github.com

Command Injection Roo Code Roocode

8.1

CVSS 3.1 · GitHub Advisory

Severity by source

GitHub Advisory PRIMARY

8.1 HIGH

AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

Attack Vector

Network

Attack Complexity

High

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Analysis Generated

Mar 28, 2026 - 19:10 vuln.today

CVE Published

Sep 05, 2025 - 23:15 nvd

HIGH 8.1

DescriptionGitHub Advisory

Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Versions below 3.26.0 contain a vulnerability in the command parsing logic where the Bash parameter expansion and indirect reference were not handled correctly. If the agent was configured to auto-approve execution of certain commands, an attacker able to influence prompts could abuse this weakness to execute additional arbitrary commands alongside the intended one. This is fixed in version 3.26.0.

AnalysisAI

Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Rated high severity (CVSS 8.1), this vulnerability is remotely exploitable, no authentication required. No vendor patch available.

Technical ContextAI

This vulnerability is classified as OS Command Injection (CWE-78), which allows attackers to execute arbitrary operating system commands on the host. Roo Code is an AI-powered autonomous coding agent that lives in users' editors. Versions below 3.26.0 contain a vulnerability in the command parsing logic where the Bash parameter expansion and indirect reference were not handled correctly. If the agent was configured to auto-approve execution of certain commands, an attacker able to influence prompts could abuse this weakness to execute additional arbitrary commands alongside the intended one. This is fixed in version 3.26.0. Affected products include: Roocode Roo Code. Version information: version 3.26.0..

RemediationAI

No vendor patch is available at time of analysis. Monitor vendor advisories for updates. Avoid passing user input to shell commands. Use language-specific APIs instead of shell execution. Apply strict input validation with allowlists.