Trycua Cli — 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": "@trycua/cli",
"source": {
"kind": "package",
"origin": "@trycua/cli"
},
"server": {
"name": "@trycua/cli"
}
},
"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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"external-sink"
]
},
"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-CAP-001",
"title": "Tool \"computer_run_command\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"computer_run_command\" appears to run shell commands or evaluate code (keyword \"run_command\" 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": "computer_run_command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/commands/serve-mcp.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/commands/serve-mcp.ts:10`): 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": "src/commands/serve-mcp.ts"
},
"evidence": "import { spawn } from 'child_process'; // Permission levels for the MCP server type Permission = | 'list_sandboxes'",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/commands/serve-mcp.ts",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/commands/skills.ts)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/commands/skills.ts:358`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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": "src/commands/skills.ts"
},
"evidence": "const response = await fetch('https://api.anthropic.com/v1/messages', { method: 'POST', headers: { 'x-api",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/commands/skills.ts",
"line": 358,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"computer_run_command\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"computer_run_command\" 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": "computer_run_command"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "list_sandboxes",
"tags": [],
"reasons": {}
},
{
"tool": "create_sandbox",
"tags": [],
"reasons": {}
},
{
"tool": "delete_sandbox",
"tags": [],
"reasons": {}
},
{
"tool": "start_sandbox",
"tags": [],
"reasons": {}
},
{
"tool": "stop_sandbox",
"tags": [],
"reasons": {}
},
{
"tool": "restart_sandbox",
"tags": [],
"reasons": {}
},
{
"tool": "suspend_sandbox",
"tags": [],
"reasons": {}
},
{
"tool": "get_sandbox",
"tags": [],
"reasons": {}
},
{
"tool": "computer_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "computer_get_screen_size",
"tags": [],
"reasons": {}
},
{
"tool": "computer_click",
"tags": [],
"reasons": {}
},
{
"tool": "computer_double_click",
"tags": [],
"reasons": {}
},
{
"tool": "computer_move",
"tags": [],
"reasons": {}
},
{
"tool": "computer_mousedown",
"tags": [],
"reasons": {}
},
{
"tool": "computer_mouseup",
"tags": [],
"reasons": {}
},
{
"tool": "computer_mousemove",
"tags": [],
"reasons": {}
},
{
"tool": "computer_type",
"tags": [],
"reasons": {}
},
{
"tool": "computer_press_key",
"tags": [],
"reasons": {}
},
{
"tool": "computer_keydown",
"tags": [],
"reasons": {}
},
{
"tool": "computer_keyup",
"tags": [],
"reasons": {}
},
{
"tool": "computer_hotkey",
"tags": [],
"reasons": {}
},
{
"tool": "computer_scroll",
"tags": [],
"reasons": {}
},
{
"tool": "computer_drag",
"tags": [],
"reasons": {}
},
{
"tool": "computer_clipboard_get",
"tags": [],
"reasons": {}
},
{
"tool": "computer_clipboard_set",
"tags": [],
"reasons": {}
},
{
"tool": "computer_run_command",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_command\" in tool name"
]
}
},
{
"tool": "computer_file_read",
"tags": [],
"reasons": {}
},
{
"tool": "computer_file_write",
"tags": [],
"reasons": {}
},
{
"tool": "computer_list_directory",
"tags": [],
"reasons": {}
},
{
"tool": "computer_open",
"tags": [],
"reasons": {}
},
{
"tool": "computer_launch_app",
"tags": [],
"reasons": {}
},
{
"tool": "computer_get_active_window",
"tags": [],
"reasons": {}
},
{
"tool": "skill_list",
"tags": [],
"reasons": {}
},
{
"tool": "skill_read",
"tags": [],
"reasons": {}
},
{
"tool": "skill_record",
"tags": [],
"reasons": {}
},
{
"tool": "skill_delete",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "f37add185599f07c17f670c2ac1ef0bee3c6c2e99f61e278dcc821bacbd651b6",
"stats": {
"tools": 36,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 1,
"low": 1,
"info": 0
}
}
}