Raw scan report

Nodriver Proxy — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.

← Back to the scan page
{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.8.0",
    "methodologyVersion": "mcptrustchecker-1.8"
  },
  "target": {
    "id": "nodriver-proxy-mcp",
    "source": {
      "kind": "package",
      "origin": "nodriver-proxy-mcp"
    },
    "server": {
      "name": "nodriver-proxy-mcp"
    }
  },
  "grade": "A",
  "score": {
    "score": 93,
    "threatScore": 100,
    "grade": "A",
    "band": "A",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "client",
        "term": "capability-exposure",
        "level": "high",
        "label": "capability blast radius (high) — client exposure if the model is manipulated",
        "appliedPenalty": 6
      },
      {
        "kind": "client",
        "term": "verification-discount",
        "level": "repo",
        "label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
        "appliedPenalty": 1
      },
      {
        "kind": "client",
        "term": "coverage-honesty",
        "level": "source",
        "label": "inspection depth (source) — how much of the target the scan could see",
        "appliedPenalty": 0
      }
    ],
    "gatesFired": [],
    "methodologyVersion": "mcptrustchecker-1.8"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "can send data / act on an external service",
      "can execute shell commands or code"
    ],
    "tags": [
      "untrusted-input",
      "external-sink",
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (39 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
    ]
  },
  "findings": [
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/nodriver_proxy_mcp/browser/session_manager.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/nodriver_proxy_mcp/browser/session_manager.py:243`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/nodriver_proxy_mcp/browser/session_manager.py"
      },
      "evidence": "True proc = subprocess.Popen(cmd, **popen_kwargs) if not self._wait_for_ipc(ipc_port, timeout=10.",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/nodriver_proxy_mcp/browser/session_manager.py",
        "line": 243,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/nodriver_proxy_mcp/codemode/tools.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/nodriver_proxy_mcp/codemode/tools.py:113`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/nodriver_proxy_mcp/codemode/tools.py"
      },
      "evidence": "try: subprocess.run( [\"taskkill\", \"/F\", \"/T\", \"/PID\", str(pid)], ca",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/nodriver_proxy_mcp/codemode/tools.py",
        "line": 113,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/nodriver_proxy_mcp/proxy/controller.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/nodriver_proxy_mcp/proxy/controller.py:91`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/nodriver_proxy_mcp/proxy/controller.py"
      },
      "evidence": "self._proc = subprocess.Popen(cmd, **popen_kwargs) self._port = port # Drain stderr in ba",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/nodriver_proxy_mcp/proxy/controller.py",
        "line": 91,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/nodriver_proxy_mcp/sdk.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/nodriver_proxy_mcp/sdk.py:682`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
      "remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
      "location": {
        "kind": "server",
        "name": "src/nodriver_proxy_mcp/sdk.py"
      },
      "evidence": "True proc = subprocess.Popen(cmd, **popen_kwargs) if not _wait_for_port(ipc_port, timeout=15.0):",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/nodriver_proxy_mcp/sdk.py",
        "line": 682,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-FLOW-005",
      "title": "Untrusted input can drive an external action",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "Untrusted-input tools ([browser_intercept_disable, browser_list_intercept_rules, list_interception_rules]) co-exist with external-action tools ([generate_curl]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
      "remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
      "location": {
        "kind": "flow",
        "name": "browser_intercept_disable → generate_curl"
      },
      "evidence": "untrusted [browser_intercept_disable, browser_list_intercept_rules, list_interception_rules] → sinks [generate_curl]",
      "owasp": "LLM06:2025 Excessive Agency",
      "references": [],
      "data": {
        "untrusted": [
          "browser_intercept_disable",
          "browser_list_intercept_rules",
          "list_interception_rules"
        ],
        "sinks": [
          "generate_curl"
        ]
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "medium",
      "confidence": "strong",
      "untrustedInput": [
        "browser_intercept_disable",
        "browser_list_intercept_rules",
        "list_interception_rules"
      ],
      "sensitiveSource": [],
      "externalSink": [
        "generate_curl"
      ],
      "selfContained": false,
      "description": "Untrusted input can drive an external action even though no sensitive source is exposed."
    }
  ],
  "capabilities": [
    {
      "tool": "browser_open",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_close",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_list_sessions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_list_tabs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_go",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_back",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_get_dom",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_get_text",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_get_storage",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_get_console",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_screenshot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_click",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_type",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_set_cookie",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_js",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_wait",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_intercept_request",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_intercept_response",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_intercept_disable",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "browser_list_intercept_rules",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "execute_security_code",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "manage_proxy",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "set_scope",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "proxy_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_traffic_summary",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "inspect_flow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_traffic",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "extract_from_flow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "clear_traffic",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "generate_curl",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"curl\""
        ]
      }
    },
    {
      "tool": "replay_flow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "send_raw_request",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "add_interception_rule",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "remove_interception_rule",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_interception_rules",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "extract_session_variable",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_session_variables",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "detect_auth_pattern",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "fuzz_endpoint",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "190b17e7d4098fbb462ecba433a240081308af0913b07825ff6dc529d29ad14e",
  "stats": {
    "tools": 39,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 4,
      "medium": 1,
      "low": 0,
      "info": 0
    }
  }
}