High severity · published Aug 22, 2025
CVE-2025-57771
Roo-Code potential remote code execution via auto-execute command parsing flaw
8.1
CVSS
0.7%
EPSS
No
On KEV
Description
Roo Code is an AI-powered autonomous coding agent that lives in users' editors. In versions prior to 3.25.5, Roo-Code fails to properly handle process substitution and single ampersand characters in the command parsing logic for auto-execute commands. If a user has enabled auto-approved execution for a command such as ls, an attacker who can submit crafted prompts to the agent may inject arbitrary commands to be executed alongside the intended command. Exploitation requires attacker access to submit prompts and for the user to have enabled auto-approved command execution, which is disabled by default. This vulnerability could allow an attacker to execute arbitrary code. The issue is fixed in version 3.25.5.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
High
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.7% · higher than 55% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
RO
Roo-Code · RooCodeInc
< 3.25.5 · source: vendor
Affected product
RO
Roo-Code
RooCodeInc
More from Roo-Code
9.8
CVE-2025-58372
Roo Code: Potential Remote Code Execution via .code-workspace
9.8
CVE-2025-58371
Roo Code is vulnerable to command injection via GitHub actions workflow
8.8
CVE-2026-110206
Roo-Code through 3.54.0 Auto-Approve Bypass via Command Substitution at Command Position
8.8
CVE-2026-110205
Roo-Code through 3.54.0 Auto-Approve Bypass via Glob Token Discarding Command Substitution
8.8
CVE-2026-110204
Roo-Code through 3.54.0 Auto-Approve Bypass via Funsub Command Substitution