« Volver al listado

CVE-2026-30304

Estado: AnalizadaCrítica (9.6)—

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be potentially destructive, it still requires user approval. However, this design is highly susceptible to prompt injection attacks. An attacker can employ a generic template to wrap any malicious command and mislead the model into misclassifying it as a 'safe' command, thereby bypassing the user approval requirement and resulting in arbitrary command execution.

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.

Requiere interacción del usuario (UI:R) para abrir/usar AI Code. Prompt injection genera ejecución arbitraria de comandos (T1059) y potencial manipulación de datos (T1565) con confidencialidad e integridad críticas.

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 SegmentationLimit Software Installation

Tecnologías afectadas (1)

Tianguaduizhang — AI Code

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-30304",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-30304",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-03-27T19:47:16.019800Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "cvssData": {
          "scope": "CHANGED",
          "version": "3.1",
          "baseScore": 9.6,
          "attackVector": "NETWORK",
          "baseSeverity": "CRITICAL",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
          "integrityImpact": "HIGH",
          "userInteraction": "REQUIRED",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "HIGH"
        },
        "impactScore": 6,
        "exploitabilityScore": 2.8
      }
    ]
  },
  "affected": [
    {
      "source": "cve@mitre.org",
      "affectedData": [
        {
          "vendor": "n/a",
          "product": "n/a",
          "versions": [
            {
              "status": "affected",
              "version": "n/a"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-03-27T15:16:53.263",
  "references": [
    {
      "url": "https://github.com/Secsys-FDU/LLM-Tool-Calling-CVEs/issues/2",
      "tags": [
        "Issue Tracking"
      ],
      "source": "cve@mitre.org"
    },
    {
      "url": "https://marketplace.visualstudio.com/items?itemName=tianguaduizhang.claude-dev-china",
      "tags": [
        "Product"
      ],
      "source": "cve@mitre.org"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "description": [
        {
          "lang": "en",
          "value": "CWE-20"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be potentially destructive, it still requires user approval. However, this design is highly susceptible to prompt injection attacks. An attacker can employ a generic template to wrap any malicious command and mislead the model into misclassifying it as a 'safe' command, thereby bypassing the user approval requirement and resulting in arbitrary command execution."
    }
  ],
  "lastModified": "2026-06-17T10:32:37.223",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:tianguaduizhang:ai_code:*:*:*:*:*:visual_studio_code:*:*",
              "vulnerable": true,
              "matchCriteriaId": "10D06419-E19B-41FE-81D5-8D4DC78D8DB9",
              "versionEndIncluding": "3.12.4"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "cve@mitre.org"
}