Microsandbox — 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": "microsandbox-mcp",
"source": {
"kind": "package",
"origin": "microsandbox-mcp"
},
"server": {
"name": "microsandbox-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-1.13"
},
"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 (69 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 \"sandbox_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"sandbox_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": "sandbox_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"sandbox_shell\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"sandbox_shell\" appears to run shell commands or evaluate code (keyword \"shell\" 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": "sandbox_shell"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"sandbox_exec_start\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"sandbox_exec_start\" 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": "sandbox_exec_start"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"sandbox_exec_poll\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"sandbox_exec_poll\" 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": "sandbox_exec_poll"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"sandbox_exec_write_stdin\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"sandbox_exec_write_stdin\" 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": "sandbox_exec_write_stdin"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"sandbox_exec_signal\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"sandbox_exec_signal\" 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": "sandbox_exec_signal"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"sandbox_exec_close\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"sandbox_exec_close\" 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": "sandbox_exec_close"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"sandbox_ssh_exec\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"sandbox_ssh_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": "sandbox_ssh_exec"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"sandbox_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"sandbox_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": "sandbox_exec"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"sandbox_shell\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"sandbox_shell\" 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": "sandbox_shell"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"sandbox_exec_start\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"sandbox_exec_start\" 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": "sandbox_exec_start"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"sandbox_exec_poll\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"sandbox_exec_poll\" 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": "sandbox_exec_poll"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"sandbox_exec_write_stdin\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"sandbox_exec_write_stdin\" 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": "sandbox_exec_write_stdin"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"sandbox_exec_signal\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"sandbox_exec_signal\" 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": "sandbox_exec_signal"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"sandbox_exec_close\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"sandbox_exec_close\" 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": "sandbox_exec_close"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"sandbox_ssh_exec\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"sandbox_ssh_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": "sandbox_ssh_exec"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "sandbox_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "sandbox_shell",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"shell\" in tool name"
]
}
},
{
"tool": "sandbox_exec_start",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "sandbox_exec_poll",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "sandbox_exec_write_stdin",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "sandbox_exec_signal",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "sandbox_exec_close",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "sandbox_fs_read",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_write",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_list",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_mkdir",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_remove",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_copy",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_rename",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_stat",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_exists",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_copy_from_host",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_fs_copy_to_host",
"tags": [],
"reasons": {}
},
{
"tool": "image_list",
"tags": [],
"reasons": {}
},
{
"tool": "image_inspect",
"tags": [],
"reasons": {}
},
{
"tool": "image_remove",
"tags": [],
"reasons": {}
},
{
"tool": "image_prune",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_logs_read",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_logs_stream",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_metrics",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_metrics_all",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_metrics_stream",
"tags": [],
"reasons": {}
},
{
"tool": "runtime_check",
"tags": [],
"reasons": {}
},
{
"tool": "runtime_install",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_run",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_create",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_start",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_list",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_status",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_inspect",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_stop",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_drain",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_wait",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_remove",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_create",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_list",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_inspect",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_verify",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_remove",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_reindex",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_save",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_load",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_ssh_exec",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"exec\" in tool name"
]
}
},
{
"tool": "sandbox_sftp_read",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_sftp_write",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_sftp_mkdir",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_sftp_remove",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_sftp_rename",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_sftp_realpath",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_sftp_readlink",
"tags": [],
"reasons": {}
},
{
"tool": "sandbox_sftp_symlink",
"tags": [],
"reasons": {}
},
{
"tool": "volume_create",
"tags": [],
"reasons": {}
},
{
"tool": "volume_list",
"tags": [],
"reasons": {}
},
{
"tool": "volume_inspect",
"tags": [],
"reasons": {}
},
{
"tool": "volume_remove",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_read",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_write",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_list",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_mkdir",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_remove",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_copy",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_rename",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_stat",
"tags": [],
"reasons": {}
},
{
"tool": "volume_fs_exists",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "6d737d5c0284fe780e034cfdf8e838d91e8f1556165d52b5c8707fb7e05b5c70",
"stats": {
"tools": 69,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 8,
"info": 0
}
}
}