Autodevice — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "autodevice-mcp",
"source": {
"kind": "package",
"origin": "autodevice-mcp"
},
"server": {
"name": "autodevice-mcp"
}
},
"grade": "A",
"score": {
"score": 92,
"threatScore": 99,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 1.2,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SUP-010",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"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-1.13"
},
"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 (50 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 (autodevice_mcp/diagnostics/harmony_speed.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/diagnostics/harmony_speed.py:41`): 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": "autodevice_mcp/diagnostics/harmony_speed.py"
},
"evidence": "r() completed = subprocess.run( command, capture_output=True, timeout=timeou",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/diagnostics/harmony_speed.py",
"line": 41,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/execution/adapters/harmony.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/execution/adapters/harmony.py:755`): 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": "autodevice_mcp/execution/adapters/harmony.py"
},
"evidence": "y: output = subprocess.check_output( command, stderr=subprocess.STDOUT, timeout=timeout",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/execution/adapters/harmony.py",
"line": 755,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/execution/adapters/hdc_worker.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/execution/adapters/hdc_worker.py:224`): 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": "autodevice_mcp/execution/adapters/hdc_worker.py"
},
"evidence": "s.\"\"\" process = subprocess.Popen( self.shell_command, stdin=subprocess.PIPE,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/execution/adapters/hdc_worker.py",
"line": 224,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/execution/command_runner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/execution/command_runner.py:32`): 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": "autodevice_mcp/execution/command_runner.py"
},
"evidence": "ate, values) return subprocess.run( argv, text=True, capture_output=True, timeout=fl",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/execution/command_runner.py",
"line": 32,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/execution/devices.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/execution/devices.py:2112`): 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": "autodevice_mcp/execution/devices.py"
},
"evidence": "output = subprocess.check_output( [\"hdc\", \"list\", \"targets\"], tex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/execution/devices.py",
"line": 2112,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/execution/preflight.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/execution/preflight.py:295`): 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": "autodevice_mcp/execution/preflight.py"
},
"evidence": "try: output = subprocess.check_output( [\"adb\", \"devices\"], text=True, stdi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/execution/preflight.py",
"line": 295,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/execution/wda_guardian.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/execution/wda_guardian.py:280`): 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": "autodevice_mcp/execution/wda_guardian.py"
},
"evidence": "ry: completed = subprocess.run( [\"idevice_id\", \"-l\"], stdin=subprocess.DEVNULL,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/execution/wda_guardian.py",
"line": 280,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/platform/network.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/platform/network.py:78`): 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": "autodevice_mcp/platform/network.py"
},
"evidence": "runner else subprocess.run( command, text=True, capture_outp",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/platform/network.py",
"line": 78,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/platform/processes.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/platform/processes.py:385`): 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": "autodevice_mcp/platform/processes.py"
},
"evidence": "completed = subprocess.run( argv, capture_output=True, text=",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/platform/processes.py",
"line": 385,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (autodevice_mcp/proxy/host_selection.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`autodevice_mcp/proxy/host_selection.py:156`): 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": "autodevice_mcp/proxy/host_selection.py"
},
"evidence": "ner(command) return subprocess.run( command, capture_output=True, text=True, timeout",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "autodevice_mcp/proxy/host_selection.py",
"line": 156,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (autodevice_mcp/mcp_tools/registry.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`autodevice_mcp/mcp_tools/registry.py:182`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "autodevice_mcp/mcp_tools/registry.py"
},
"evidence": "try: __import__(name) deps[name] = True except Exception as exc:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "autodevice_mcp/mcp_tools/registry.py",
"line": 182,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-010",
"title": "Package runs install-time scripts (postinstall)",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"description": "\"autodevice-mcp\" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.",
"remediation": "Review the scripts; install with --ignore-scripts where possible and vet what they do.",
"location": {
"kind": "package",
"name": "autodevice-mcp"
},
"evidence": "node scripts/postinstall.js",
"owasp": "LLM03:2025 Supply Chain",
"references": [
"https://github.com/ossf/package-analysis",
"https://owasp.org/www-project-top-10-ci-cd-security-risks/"
],
"data": {
"scripts": [
"postinstall"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "launch_app",
"tags": [],
"reasons": {}
},
{
"tool": "get_current_app",
"tags": [],
"reasons": {}
},
{
"tool": "list_elements",
"tags": [],
"reasons": {}
},
{
"tool": "click",
"tags": [],
"reasons": {}
},
{
"tool": "click_and_assert",
"tags": [],
"reasons": {}
},
{
"tool": "swipe",
"tags": [],
"reasons": {}
},
{
"tool": "long_press",
"tags": [],
"reasons": {}
},
{
"tool": "input_text",
"tags": [],
"reasons": {}
},
{
"tool": "smart_click",
"tags": [],
"reasons": {}
},
{
"tool": "intent_click",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "navigate_path",
"tags": [],
"reasons": {}
},
{
"tool": "doctor",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_contract",
"tags": [],
"reasons": {}
},
{
"tool": "diagnose_environment",
"tags": [],
"reasons": {}
},
{
"tool": "runtime_status",
"tags": [],
"reasons": {}
},
{
"tool": "execution_events",
"tags": [],
"reasons": {}
},
{
"tool": "execution_status",
"tags": [],
"reasons": {}
},
{
"tool": "prepare_run",
"tags": [],
"reasons": {}
},
{
"tool": "preflight",
"tags": [],
"reasons": {}
},
{
"tool": "repair_wda",
"tags": [],
"reasons": {}
},
{
"tool": "device_status",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_cases",
"tags": [],
"reasons": {}
},
{
"tool": "submit_case_candidates",
"tags": [],
"reasons": {}
},
{
"tool": "import_cases",
"tags": [],
"reasons": {}
},
{
"tool": "list_rules",
"tags": [],
"reasons": {}
},
{
"tool": "rule_preview",
"tags": [],
"reasons": {}
},
{
"tool": "apply_case_asset_overrides",
"tags": [],
"reasons": {}
},
{
"tool": "start_run",
"tags": [],
"reasons": {}
},
{
"tool": "record_result",
"tags": [],
"reasons": {}
},
{
"tool": "get_run_status",
"tags": [],
"reasons": {}
},
{
"tool": "export_report",
"tags": [],
"reasons": {}
},
{
"tool": "report_server_status",
"tags": [],
"reasons": {}
},
{
"tool": "stop_report_server",
"tags": [],
"reasons": {}
},
{
"tool": "latest_report",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_trace",
"tags": [],
"reasons": {}
},
{
"tool": "run_cases",
"tags": [],
"reasons": {}
},
{
"tool": "start_proxy_runtime",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_runtime_status",
"tags": [],
"reasons": {}
},
{
"tool": "stop_proxy_runtime",
"tags": [],
"reasons": {}
},
{
"tool": "restore_device_proxy",
"tags": [],
"reasons": {}
},
{
"tool": "record_navigation_path",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_navigation_path",
"tags": [],
"reasons": {}
},
{
"tool": "record_field_alias",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_field_alias",
"tags": [],
"reasons": {}
},
{
"tool": "review_session",
"tags": [],
"reasons": {}
},
{
"tool": "apply_manual_reviews",
"tags": [],
"reasons": {}
},
{
"tool": "prepare_visual_review",
"tags": [],
"reasons": {}
},
{
"tool": "run_visual_comparison",
"tags": [],
"reasons": {}
},
{
"tool": "apply_visual_reviews",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d5b34c41489586a165b4fff2ad2eebb1894ef0ec7881ee628109c5d459cb7507",
"stats": {
"tools": 50,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 1,
"low": 1,
"info": 0
}
}
}