CVE-2025-58370

05.09.2025, 23:15

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.

OS Command Injection

Provider	Type	Base Score	Atk. Vector	Atk. Complexity	Priv. Required	Vector
NIST	NIST	8.1 HIGH	NETWORK	HIGH	NONE	CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub_M	CNA	8.1 HIGH	NETWORK	HIGH	NONE	CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
CISA-ADP	ADP	---				---

Base Score

CVSS 3.x

EPSS Score

Percentile: 37%

Vendor	Product	Version
roocode	roo_code	𝑥 < 3.26.0

𝑥

= Vulnerable software versions

Common Weakness Enumeration

CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
The software 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.

References

https://github.com/RooCodeInc/Roo-Code/security/advisories/GHSA-2rm5-cvcm-7592