{"dataType": "CVE_RECORD", "dataVersion": "5.1", "cveMetadata": {"cveId": "CVE-2025-53098", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "state": "PUBLISHED", "assignerShortName": "GitHub_M", "dateReserved": "2025-06-25T13:41:23.086Z", "datePublished": "2025-06-27T21:43:35.031Z", "dateUpdated": "2025-07-03T14:27:54.220Z"}, "containers": {"cna": {"title": "Roo Code Vulnerable to Potential Remote Code Execution via Model Context Protocol", "problemTypes": [{"descriptions": [{"cweId": "CWE-77", "lang": "en", "description": "CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection')", "type": "CWE"}]}], "metrics": [{"cvssV3_1": {"attackComplexity": "HIGH", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 8.1, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H", "version": "3.1"}}], "references": [{"name": "https://github.com/RooCodeInc/Roo-Code/security/advisories/GHSA-5x8h-m52g-5v54", "tags": ["x_refsource_CONFIRM"], "url": "https://github.com/RooCodeInc/Roo-Code/security/advisories/GHSA-5x8h-m52g-5v54"}, {"name": "https://github.com/RooCodeInc/Roo-Code/commit/7d0b22f9e659dc6c26aab0bacbea27874986e772", "tags": ["x_refsource_MISC"], "url": "https://github.com/RooCodeInc/Roo-Code/commit/7d0b22f9e659dc6c26aab0bacbea27874986e772"}], "affected": [{"vendor": "RooCodeInc", "product": "Roo-Code", "versions": [{"version": "< 3.20.3", "status": "affected"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-07-01T13:59:57.913Z"}, "descriptions": [{"lang": "en", "value": "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 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."}], "source": {"advisory": "GHSA-5x8h-m52g-5v54", "discovery": "UNKNOWN"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2025-07-03T14:27:45.502230Z", "id": "CVE-2025-53098", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-07-03T14:27:54.220Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2025-53098", "role": "CISA Coordinator", "options": [{"Exploitation": "none"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "version": "2.0.3", "timestamp": "2025-07-03T14:27:45.502230Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-06-30T16:21:57.291Z"}}], "cna": {"title": "Roo Code Vulnerable to Potential Remote Code Execution via Model Context Protocol", "source": {"advisory": "GHSA-5x8h-m52g-5v54", "discovery": "UNKNOWN"}, "metrics": [{"cvssV3_1": {"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"}}], "affected": [{"vendor": "RooCodeInc", "product": "Roo-Code", "versions": [{"status": "affected", "version": "< 3.20.3"}]}], "references": [{"url": "https://github.com/RooCodeInc/Roo-Code/security/advisories/GHSA-5x8h-m52g-5v54", "name": "https://github.com/RooCodeInc/Roo-Code/security/advisories/GHSA-5x8h-m52g-5v54", "tags": ["x_refsource_CONFIRM"]}, {"url": "https://github.com/RooCodeInc/Roo-Code/commit/7d0b22f9e659dc6c26aab0bacbea27874986e772", "name": "https://github.com/RooCodeInc/Roo-Code/commit/7d0b22f9e659dc6c26aab0bacbea27874986e772", "tags": ["x_refsource_MISC"]}], "descriptions": [{"lang": "en", "value": "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 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."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-77", "description": "CWE-77: Improper Neutralization of Special Elements used in a Command ('Command Injection')"}]}], "providerMetadata": {"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "shortName": "GitHub_M", "dateUpdated": "2025-07-01T13:59:57.913Z"}}}, "cveMetadata": {"cveId": "CVE-2025-53098", "state": "PUBLISHED", "dateUpdated": "2025-07-03T14:27:54.220Z", "dateReserved": "2025-06-25T13:41:23.086Z", "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa", "datePublished": "2025-06-27T21:43:35.031Z", "assignerShortName": "GitHub_M"}, "dataVersion": "5.1"}

{"cveTags": [], "descriptions": [{"lang": "en", "value": "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 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."}, {"lang": "es", "value": "Roo Code es un agente de codificaci\u00f3n aut\u00f3nomo basado en IA. La configuraci\u00f3n de MCP espec\u00edfica del proyecto para el agente de Roo Code se almacena en el archivo `.roo/mcp.json` dentro del espacio de trabajo de VS Code. Dado que el formato de configuraci\u00f3n de MCP permite la ejecuci\u00f3n de comandos arbitrarios, antes de la versi\u00f3n 3.20.3, un atacante con acceso habr\u00eda podido manipular un mensaje para solicitar al agente que escribiera un comando malicioso en el archivo de configuraci\u00f3n de MCP. Si el usuario hubiera habilitado la aprobaci\u00f3n autom\u00e1tica de escrituras de archivos dentro del proyecto, esto habr\u00eda provocado la ejecuci\u00f3n de comandos arbitrarios. Este problema es de gravedad moderada, ya que requiere que el atacante ya pueda enviar mensajes al agente (por ejemplo, mediante un ataque de inyecci\u00f3n de mensajes), que el usuario tenga MCP habilitado (activado por defecto) y que tenga habilitada la aprobaci\u00f3n autom\u00e1tica de escrituras de archivos (desactivada por defecto). La versi\u00f3n 3.20.3 corrige el problema agregando una capa adicional de configuraci\u00f3n opt-in para aprobar autom\u00e1ticamente la escritura en los archivos de configuraci\u00f3n de Roo, incluidos todos los archivos dentro de la carpeta `.roo/`."}], "id": "CVE-2025-53098", "lastModified": "2025-07-01T14:15:40.843", "metrics": {"cvssMetricV31": [{"cvssData": {"attackComplexity": "HIGH", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 8.1, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H", "version": "3.1"}, "exploitabilityScore": 2.2, "impactScore": 5.9, "source": "security-advisories@github.com", "type": "Secondary"}]}, "published": "2025-06-27T22:15:25.993", "references": [{"source": "security-advisories@github.com", "url": "https://github.com/RooCodeInc/Roo-Code/commit/7d0b22f9e659dc6c26aab0bacbea27874986e772"}, {"source": "security-advisories@github.com", "url": "https://github.com/RooCodeInc/Roo-Code/security/advisories/GHSA-5x8h-m52g-5v54"}], "sourceIdentifier": "security-advisories@github.com", "vulnStatus": "Awaiting Analysis", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-77"}], "source": "security-advisories@github.com", "type": "Secondary"}]}

{}