Maestro — 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.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "@luxurylabs/maestro-mcp",
"source": {
"kind": "package",
"origin": "@luxurylabs/maestro-mcp"
},
"server": {
"name": "@luxurylabs/maestro-mcp"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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 (34 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 (dist/maestro/android-device.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/maestro/android-device.js:1`): 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": "dist/maestro/android-device.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import { accessSync, constants } from \"no",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/maestro/android-device.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/maestro/cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/maestro/cli.js:1`): 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": "dist/maestro/cli.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import { accessSync, constants } from \"no",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/maestro/cli.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/maestro/ios-simulator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/maestro/ios-simulator.js:1`): 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": "dist/maestro/ios-simulator.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import fs from \"node:fs/promises\"; import",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/maestro/ios-simulator.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/plugins/loader.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/plugins/loader.js:101`): 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": "dist/plugins/loader.js"
},
"evidence": "const mod = (await import(importTarget)); const plugin = (mod.default ?? mod); if (!plugin || typeof plugin",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/plugins/loader.js",
"line": 101,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/utils/setup.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/utils/setup.js:1`): 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": "dist/utils/setup.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import { accessSync, constants } from \"no",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/utils/setup.js",
"line": 1,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "hello_world",
"tags": [],
"reasons": {}
},
{
"tool": "example_maestro_version",
"tags": [],
"reasons": {}
},
{
"tool": "maestro_status",
"tags": [],
"reasons": {}
},
{
"tool": "setup",
"tags": [],
"reasons": {}
},
{
"tool": "install_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_devices",
"tags": [],
"reasons": {}
},
{
"tool": "device_info",
"tags": [],
"reasons": {}
},
{
"tool": "launch_app",
"tags": [],
"reasons": {}
},
{
"tool": "stop_app",
"tags": [],
"reasons": {}
},
{
"tool": "install_app",
"tags": [],
"reasons": {}
},
{
"tool": "take_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "tap",
"tags": [],
"reasons": {}
},
{
"tool": "input_text",
"tags": [],
"reasons": {}
},
{
"tool": "swipe",
"tags": [],
"reasons": {}
},
{
"tool": "assert_visible",
"tags": [],
"reasons": {}
},
{
"tool": "scroll_to",
"tags": [],
"reasons": {}
},
{
"tool": "press_back",
"tags": [],
"reasons": {}
},
{
"tool": "run_flow",
"tags": [],
"reasons": {}
},
{
"tool": "generate_and_run_flow",
"tags": [],
"reasons": {}
},
{
"tool": "generate_test",
"tags": [],
"reasons": {}
},
{
"tool": "list_virtual_devices",
"tags": [],
"reasons": {}
},
{
"tool": "boot_device",
"tags": [],
"reasons": {}
},
{
"tool": "shutdown_device",
"tags": [],
"reasons": {}
},
{
"tool": "open_url",
"tags": [],
"reasons": {}
},
{
"tool": "set_permissions",
"tags": [],
"reasons": {}
},
{
"tool": "send_push",
"tags": [],
"reasons": {}
},
{
"tool": "override_status_bar",
"tags": [],
"reasons": {}
},
{
"tool": "set_location",
"tags": [],
"reasons": {}
},
{
"tool": "create_device",
"tags": [],
"reasons": {}
},
{
"tool": "delete_device",
"tags": [],
"reasons": {}
},
{
"tool": "scan_project",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_source_file",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_flows",
"tags": [],
"reasons": {}
},
{
"tool": "clean_flows",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "060cfd5be335a559607be52f50b303382454a45df435140f04f2d1d7ba029bde",
"stats": {
"tools": 34,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 1,
"low": 1,
"info": 0
}
}
}