« Volver al listado

CVE-2026-29783

Estado: AnalizadaAlta (7.5)—

The shell tool within GitHub Copilot CLI versions prior to and including 0.0.422 can allow arbitrary code execution through crafted bash parameter expansion patterns. An attacker who can influence the commands executed by the agent (e.g., via prompt injection through repository files, MCP server responses, or user instructions) can exploit bash parameter transformation operators to execute hidden commands, bypassing the safety assessment that classifies commands as "read-only." This has been patched in version 0.0.423.

The vulnerability stems from how the CLI's shell safety assessment evaluates commands before execution.

Leer descripción completaMostrar menos

The safety layer parses and classifies shell commands as either read-only (safe) or write-capable (requires user approval). However, several bash parameter expansion features can embed executable code within arguments to otherwise read-only commands, causing them to appear safe while actually performing arbitrary operations.

The specific dangerous patterns are ${var@P}, ${var=value} / ${var:=value}, ${!var}, and nested $(cmd) or <(cmd) inside ${...} expansions. An attacker who can influence command text sent to the shell tool - for example, through prompt injection via malicious repository content (README files, code comments, issue bodies), compromised or malicious MCP server responses, or crafted user instructions containing obfuscated commands - could achieve arbitrary code execution on the user's workstation. This is possible even in permission modes that require user approval for write operations, since the commands can appear to use only read-only utilities to ultimately trigger write operations. Successful exploitation could lead to data exfiltration, file modification, or further system compromise.

CVSS

Probabilidad de explotación (EPSS)

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.

UI:A (requiere interacción del usuario) indica explotación en cliente; bash parameter expansion permite ejecución de código arbitrario; posibles exfiltración de datos y modificación de archivos.

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

Restrict Web-Based ContentRestrict File and Directory PermissionsPrivileged Account ManagementRemote Data StorageNetwork Intrusion PreventionLimit Software Installation

Tecnologías afectadas (1)

Github — Copilot Command Line Interface

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-29783",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-29783",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-03-10T00:00:00+00:00"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Primary",
        "source": "nvd@nist.gov",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 7.8,
          "attackVector": "LOCAL",
          "baseSeverity": "HIGH",
          "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
          "integrityImpact": "HIGH",
          "userInteraction": "REQUIRED",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "HIGH"
        },
        "impactScore": 5.9,
        "exploitabilityScore": 1.8
      }
    ],
    "cvssMetricV40": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "Safety": "NOT_DEFINED",
          "version": "4.0",
          "Recovery": "NOT_DEFINED",
          "baseScore": 7.5,
          "Automatable": "NOT_DEFINED",
          "attackVector": "NETWORK",
          "baseSeverity": "HIGH",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
          "exploitMaturity": "NOT_DEFINED",
          "providerUrgency": "NOT_DEFINED",
          "userInteraction": "ACTIVE",
          "attackComplexity": "LOW",
          "attackRequirements": "PRESENT",
          "privilegesRequired": "NONE",
          "subIntegrityImpact": "NONE",
          "vulnIntegrityImpact": "HIGH",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "subAvailabilityImpact": "NONE",
          "vulnAvailabilityImpact": "HIGH",
          "availabilityRequirement": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "subConfidentialityImpact": "NONE",
          "vulnConfidentialityImpact": "HIGH",
          "confidentialityRequirement": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "vulnerabilityResponseEffort": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED"
        }
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "github",
          "product": "copilot-cli",
          "versions": [
            {
              "status": "affected",
              "version": "<= 0.0.422"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-03-06T17:16:35.487",
  "references": [
    {
      "url": "https://github.com/github/copilot-cli/releases/tag/v0.0.423",
      "tags": [
        "Release Notes"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/github/copilot-cli/security/advisories/GHSA-g8r9-g2v8-jv6f",
      "tags": [
        "Exploit",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-78"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "The shell tool within GitHub Copilot CLI versions prior to and including 0.0.422 can allow arbitrary code execution through crafted bash parameter expansion patterns. An attacker who can influence the commands executed by the agent (e.g., via prompt injection through repository files, MCP server responses, or user instructions) can exploit bash parameter transformation operators to execute hidden commands, bypassing the safety assessment that classifies commands as \"read-only.\" This has been patched in version 0.0.423. \n\nThe vulnerability stems from how the CLI's shell safety assessment evaluates commands before execution. The safety layer parses and classifies shell commands as either read-only (safe) or write-capable (requires user approval). However, several bash parameter expansion features can embed executable code within arguments to otherwise read-only commands, causing them to appear safe while actually performing arbitrary operations.\n\nThe specific dangerous patterns are ${var@P}, ${var=value} / ${var:=value}, ${!var}, and nested $(cmd) or <(cmd) inside ${...} expansions. An attacker who can influence command text sent to the shell tool - for example, through prompt injection via malicious repository content (README files, code comments, issue bodies), compromised or malicious MCP server responses, or crafted user instructions containing obfuscated commands - could achieve arbitrary code execution on the user's workstation. This is possible even in permission modes that require user approval for write operations, since the commands can appear to use only read-only utilities to ultimately trigger write operations. Successful exploitation could lead to data exfiltration, file modification, or further system compromise."
    },
    {
      "lang": "es",
      "value": "La herramienta de shell en las versiones de GitHub Copilot CLI anteriores e incluyendo la 0.0.422 puede permitir la ejecución de código arbitrario a través de patrones de expansión de parámetros de bash manipulados. Un atacante que puede influir en los comandos ejecutados por el agente (por ejemplo, a través de inyección de prompt mediante archivos de repositorio, respuestas del servidor MCP o instrucciones del usuario) puede explotar los operadores de transformación de parámetros de bash para ejecutar comandos ocultos, eludiendo la evaluación de seguridad que clasifica los comandos como 'solo lectura'. Esto ha sido parcheado en la versión 0.0.423.\n\nLa vulnerabilidad se deriva de cómo la evaluación de seguridad de shell de la CLI evalúa los comandos antes de la ejecución. La capa de seguridad analiza y clasifica los comandos de shell como de solo lectura (seguros) o con capacidad de escritura (requiere aprobación del usuario). Sin embargo, varias características de expansión de parámetros de bash pueden incrustar código ejecutable dentro de argumentos de comandos que de otro modo serían de solo lectura, haciendo que parezcan seguros mientras que en realidad realizan operaciones arbitrarias.\n\nLos patrones peligrosos específicos son ${var@P}, ${var=value} / ${var:=value}, ${!var}, y $(cmd) o &lt;(cmd) anidados dentro de expansiones ${...}. Un atacante que puede influir en el texto de comando enviado a la herramienta de shell - por ejemplo, a través de inyección de prompt mediante contenido de repositorio malicioso (archivos README, comentarios de código, cuerpos de incidencias), respuestas de servidor MCP comprometidas o maliciosas, o instrucciones de usuario manipuladas que contengan comandos ofuscados - podría lograr ejecución de código arbitrario en la estación de trabajo del usuario. Esto es posible incluso en modos de permiso que requieren la aprobación del usuario para operaciones de escritura, ya que los comandos pueden parecer usar solo utilidades de solo lectura para finalmente desencadenar operaciones de escritura. La explotación exitosa podría conducir a la exfiltración de datos, modificación de archivos o un compromiso adicional del sistema."
    }
  ],
  "lastModified": "2026-06-17T10:29:52.700",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:github:copilot_command_line_interface:*:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "83686E02-90BA-4DD7-96D1-37799C3B04CE",
              "versionEndExcluding": "0.0.423"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}