Virtualbox — 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": "mcp-virtualbox",
"source": {
"kind": "package",
"origin": "mcp-virtualbox"
},
"server": {
"name": "mcp-virtualbox"
}
},
"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-1.13"
},
"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 (30 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-CAP-001",
"title": "Tool \"vm_guest_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"vm_guest_exec\" appears to run shell commands or evaluate code (keyword \"exec\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "vm_guest_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"vm_exec_ssh\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"vm_exec_ssh\" appears to run shell commands or evaluate code (keyword \"exec\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "vm_exec_ssh"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"vm_exec_winrm\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"vm_exec_winrm\" appears to run shell commands or evaluate code (keyword \"exec\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "vm_exec_winrm"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/tools/input.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/input.js:2`): 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/tools/input.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { vboxManage, formatError } from \"../vbox.js\"; import { resolveScancodes,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/input.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/vbox.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/vbox.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/vbox.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { config } from \"./types.js\"; export class VBoxError extends Error {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/vbox.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"vm_guest_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vm_guest_exec\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "vm_guest_exec"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"vm_exec_ssh\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vm_exec_ssh\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "vm_exec_ssh"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"vm_exec_winrm\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vm_exec_winrm\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "vm_exec_winrm"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "vm_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "vm_screen_info",
"tags": [],
"reasons": {}
},
{
"tool": "vm_guest_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "vm_guest_copy_to",
"tags": [],
"reasons": {}
},
{
"tool": "vm_guest_copy_from",
"tags": [],
"reasons": {}
},
{
"tool": "vm_keyboard_scancode",
"tags": [],
"reasons": {}
},
{
"tool": "vm_keyboard_type",
"tags": [],
"reasons": {}
},
{
"tool": "vm_mouse_click",
"tags": [],
"reasons": {}
},
{
"tool": "vm_install_guide",
"tags": [],
"reasons": {}
},
{
"tool": "vm_list",
"tags": [],
"reasons": {}
},
{
"tool": "vm_info",
"tags": [],
"reasons": {}
},
{
"tool": "vm_create",
"tags": [],
"reasons": {}
},
{
"tool": "vm_start",
"tags": [],
"reasons": {}
},
{
"tool": "vm_stop",
"tags": [],
"reasons": {}
},
{
"tool": "vm_delete",
"tags": [],
"reasons": {}
},
{
"tool": "vm_pause",
"tags": [],
"reasons": {}
},
{
"tool": "vm_resume",
"tags": [],
"reasons": {}
},
{
"tool": "vm_reset",
"tags": [],
"reasons": {}
},
{
"tool": "vm_shared_folder_add",
"tags": [],
"reasons": {}
},
{
"tool": "vm_shared_folder_remove",
"tags": [],
"reasons": {}
},
{
"tool": "vm_attach_media",
"tags": [],
"reasons": {}
},
{
"tool": "vm_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "vm_modify",
"tags": [],
"reasons": {}
},
{
"tool": "vm_list_ostypes",
"tags": [],
"reasons": {}
},
{
"tool": "vm_exec_ssh",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "vm_exec_winrm",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "vm_get_guest_ip",
"tags": [],
"reasons": {}
},
{
"tool": "vm_wait_for_guest_additions",
"tags": [],
"reasons": {}
},
{
"tool": "vm_wait_for_network",
"tags": [],
"reasons": {}
},
{
"tool": "vm_add_nat_port_forward",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "674b8420d97f8abeb6321db9f3635369b889543b13487b751e94993d099a5655",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 3,
"info": 0
}
}
}