Raw scan report

Mobile Mcp Ai — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, 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": "1.9.0",
    "methodologyVersion": "mcptrustchecker-1.9"
  },
  "target": {
    "id": "mobile-mcp-ai",
    "source": {
      "kind": "package",
      "origin": "mobile-mcp-ai"
    },
    "server": {
      "name": "mobile-mcp-ai"
    }
  },
  "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-1.9"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "can execute shell commands or code"
    ],
    "tags": [
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (36 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 (mobile_mcp/core/basic_tools_lite.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mobile_mcp/core/basic_tools_lite.py:1191`): 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": "mobile_mcp/core/basic_tools_lite.py"
      },
      "evidence": "''' subprocess.run([\"osascript\", \"-e\", script], check=True) time.sleep(0.3)",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mobile_mcp/core/basic_tools_lite.py",
        "line": 1191,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mobile_mcp/core/device_manager.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mobile_mcp/core/device_manager.py:80`): 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": "mobile_mcp/core/device_manager.py"
      },
      "evidence": "y: result = subprocess.run(['adb', 'version'], capture_output=True, timeout=2) if result.returnc",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mobile_mcp/core/device_manager.py",
        "line": 80,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mobile_mcp/core/ios_device_manager_wda.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mobile_mcp/core/ios_device_manager_wda.py:84`): 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": "mobile_mcp/core/ios_device_manager_wda.py"
      },
      "evidence": "ce result = subprocess.run( [sys.executable, '-m', 'tidevice', 'list', '--json'],",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mobile_mcp/core/ios_device_manager_wda.py",
        "line": 84,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (mobile_mcp/core/mobile_client.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`mobile_mcp/core/mobile_client.py:97`): 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": "mobile_mcp/core/mobile_client.py"
      },
      "evidence": "# 先禁用自动旋转 subprocess.run( ['adb', '-s', device_id, 'shell', 'settings', 'put', 'system', '",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "mobile_mcp/core/mobile_client.py",
        "line": 97,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SUP-012",
      "title": "Package has no license",
      "category": "hygiene",
      "severity": "info",
      "confidence": "strong",
      "description": "\"mobile-mcp-ai\" has no declared license. This is a legal/reuse concern, not a security finding.",
      "location": {
        "kind": "package",
        "name": "mobile-mcp-ai"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "mobile_list_elements",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_find_nearby",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_take_screenshot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_screenshot_with_som",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_click_by_som",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_click_by_text",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_click_by_id",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_click_by_percent",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_click_by_bounds",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_long_press_by_text",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_long_press_by_id",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_input_text_by_id",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_swipe",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_drag_progress_bar",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_press_key",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_wait",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_hide_keyboard",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_launch_app",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_terminate_app",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_list_apps",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_list_devices",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_check_connection",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_close_popup",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_assert_text",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_start_toast_watch",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_assert_toast",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_clear_operation_history",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_generate_test_script",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_template_add",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_get_current_app",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_open_deep_link",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_get_clipboard",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_set_clipboard",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_start_screen_record",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_stop_screen_record",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mobile_open_new_chat",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "dbd343fccd1b7f16b2b02487f53da7711565b5f9efe1567cf2728cff6a427bd2",
  "stats": {
    "tools": 36,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 4,
      "medium": 0,
      "low": 0,
      "info": 1
    }
  }
}