CVE-2025-57771
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
- Versión: 3.1
- Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
- Puntuación base: 8.1
Probabilidad de explotación (EPSS)
- Probabilidad de explotación en los próximos 30 días: 0.75%
- Percentil entre todas las CVEs puntuadas: 53
- Fecha de la puntuación: 3/10/2026
EPSS (Exploit Prediction Scoring System, de FIRST) estima la probabilidad de que una vulnerabilidad sea explotada en 30 días. Complementa a CVSS (impacto) y a CISA KEV (explotación confirmada).
🎯 Técnicas ATT&CK
Cómo se explota esta vulnerabilidad y qué consigue el atacante, en el lenguaje de MITRE ATT&CK.
- Explotación
T1190Exploit Public-Facing Applicationinitial access75 % - Impacto principal
T1059Command and Scripting Interpreterexecution85 % - Impacto secundario
T1565Data Manipulationimpact45 %
Vector AV:N (red sin privilegios) y CWE-78 (command injection) sustentan T1190. Inyección de comandos con auto-execute habilitado permite T1059 (ejecución arbitraria).
Inferido por nuestro agente de análisis a partir de la descripción oficial, el vector CVSS y la CWE, y comprobado por un supervisor. Puede contener errores.
🛡️ Mitigaciones ATT&CK que cubren estas técnicas
Tecnologías afectadas (1)
⚠ Inferidas por IA a partir de la descripción — NVD aún no ha analizado esta CVE; no son CPE verificados.
CWE
- CWE-78
Referencias
JSON original (NVD)
Mostrar
{
"id": "CVE-2025-57771",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2025-57771",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "yes"
},
{
"technicalImpact": "total"
}
],
"version": "2.0.3",
"timestamp": "2025-08-22T20:03:36.094820Z"
}
}
],
"cvssMetricV31": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"cvssData": {
"scope": "UNCHANGED",
"version": "3.1",
"baseScore": 8.1,
"attackVector": "NETWORK",
"baseSeverity": "HIGH",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H",
"integrityImpact": "HIGH",
"userInteraction": "NONE",
"attackComplexity": "HIGH",
"availabilityImpact": "HIGH",
"privilegesRequired": "NONE",
"confidentialityImpact": "HIGH"
},
"impactScore": 5.9,
"exploitabilityScore": 2.2
}
]
},
"affected": [
{
"source": "security-advisories@github.com",
"affectedData": [
{
"vendor": "RooCodeInc",
"product": "Roo-Code",
"versions": [
{
"status": "affected",
"version": "< 3.25.5"
}
]
}
]
}
],
"published": "2025-08-22T17:15:36.183",
"references": [
{
"url": "https://github.com/RooCodeInc/Roo-Code/commit/de359a465c67aefc67553aa2b464591b602c4bdc",
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/RooCodeInc/Roo-Code/security/advisories/GHSA-wrh9-463x-7wvv",
"source": "security-advisories@github.com"
}
],
"vulnStatus": "Deferred",
"weaknesses": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"description": [
{
"lang": "en",
"value": "CWE-78"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "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."
},
{
"lang": "es",
"value": "Roo Code es un agente de codificación autónomo basado en IA que reside en los editores de los usuarios. En versiones anteriores a la 3.25.5, Roo Code no gestiona correctamente la sustitución de procesos ni los caracteres \"&\" individuales en la lógica de análisis de comandos para la ejecución automática. Si un usuario ha habilitado la ejecución automática para un comando como \"ls\", un atacante que pueda enviar solicitudes manipuladas al agente podría inyectar comandos arbitrarios para que se ejecuten junto con el comando deseado. Para explotar esta vulnerabilidad, el atacante debe tener acceso para enviar solicitudes y que el usuario haya habilitado la ejecución automática de comandos, que está deshabilitada por defecto. Esta vulnerabilidad podría permitir que un atacante ejecute código arbitrario. El problema se solucionó en la versión 3.25.5."
}
],
"lastModified": "2026-06-17T09:43:24.223",
"sourceIdentifier": "security-advisories@github.com"
}