Klyk — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "klyk",
"source": {
"kind": "package",
"origin": "klyk"
},
"server": {
"name": "klyk"
}
},
"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-1.8"
},
"capability": {
"level": "high",
"reasons": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (48 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 (klyk/capture.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`klyk/capture.py:585`): 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": "klyk/capture.py"
},
"evidence": "try: result = subprocess.run( [\"system_profiler\", \"SPDisplaysDataType\"], capture_outpu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "klyk/capture.py",
"line": 585,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (klyk/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`klyk/cli.py:172`): 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": "klyk/cli.py"
},
"evidence": "e) try: r = subprocess.run(cmd, capture_output=True, text=True) except FileNotFoundError: print(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "klyk/cli.py",
"line": 172,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (klyk/client.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`klyk/client.py:73`): 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": "klyk/client.py"
},
"evidence": ") self._proc = subprocess.Popen( self._cmd, stdin=subprocess.PIPE, stdout=s",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "klyk/client.py",
"line": 73,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (klyk/computer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`klyk/computer.py:520`): 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": "klyk/computer.py"
},
"evidence": "( None, lambda: subprocess.run([\"osascript\", \"-e\", script], capture_output=True, timeout=3) ) await asyn",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "klyk/computer.py",
"line": 520,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (klyk/doctor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`klyk/doctor.py:314`): 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": "klyk/doctor.py"
},
"evidence": "f.name result = subprocess.run( [\"screencapture\", \"-x\", \"-t\", \"png\", tmp_path], capture_",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "klyk/doctor.py",
"line": 314,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (klyk/launcher.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`klyk/launcher.py:175`): 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": "klyk/launcher.py"
},
"evidence": "n None result = subprocess.run( [\"osascript\", \"-e\", script], capture_output=True, text=T",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "klyk/launcher.py",
"line": 175,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (klyk/session.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`klyk/session.py:315`): 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": "klyk/session.py"
},
"evidence": "result = subprocess.run( [\"mdfind\", f\"kMDItemFSName == '{fs_name}'\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "klyk/session.py",
"line": 315,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "inspect",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "click",
"tags": [],
"reasons": {}
},
{
"tool": "double_click",
"tags": [],
"reasons": {}
},
{
"tool": "triple_click",
"tags": [],
"reasons": {}
},
{
"tool": "long_press",
"tags": [],
"reasons": {}
},
{
"tool": "ax_action",
"tags": [],
"reasons": {}
},
{
"tool": "drag",
"tags": [],
"reasons": {}
},
{
"tool": "drag_to_element",
"tags": [],
"reasons": {}
},
{
"tool": "fill_field",
"tags": [],
"reasons": {}
},
{
"tool": "type_text",
"tags": [],
"reasons": {}
},
{
"tool": "press_key",
"tags": [],
"reasons": {}
},
{
"tool": "hold_key",
"tags": [],
"reasons": {}
},
{
"tool": "press_system_key",
"tags": [],
"reasons": {}
},
{
"tool": "scroll",
"tags": [],
"reasons": {}
},
{
"tool": "move_cursor",
"tags": [],
"reasons": {}
},
{
"tool": "wait",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for",
"tags": [],
"reasons": {}
},
{
"tool": "get_logs",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_logs\""
]
}
},
{
"tool": "read_element",
"tags": [],
"reasons": {}
},
{
"tool": "get_pixel",
"tags": [],
"reasons": {}
},
{
"tool": "get_pixels",
"tags": [],
"reasons": {}
},
{
"tool": "read_grid",
"tags": [],
"reasons": {}
},
{
"tool": "set_clipboard",
"tags": [],
"reasons": {}
},
{
"tool": "get_clipboard",
"tags": [],
"reasons": {}
},
{
"tool": "click_menu",
"tags": [],
"reasons": {}
},
{
"tool": "context_menu_select",
"tags": [],
"reasons": {}
},
{
"tool": "set_window_bounds",
"tags": [],
"reasons": {}
},
{
"tool": "verdict",
"tags": [],
"reasons": {}
},
{
"tool": "handle_system_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "close_app",
"tags": [],
"reasons": {}
},
{
"tool": "close_apps",
"tags": [],
"reasons": {}
},
{
"tool": "resume",
"tags": [],
"reasons": {}
},
{
"tool": "list_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "get_escalation_log",
"tags": [],
"reasons": {}
},
{
"tool": "set_mode",
"tags": [],
"reasons": {}
},
{
"tool": "list_windows",
"tags": [],
"reasons": {}
},
{
"tool": "focus_window",
"tags": [],
"reasons": {}
},
{
"tool": "screen_info",
"tags": [],
"reasons": {}
},
{
"tool": "take_control",
"tags": [],
"reasons": {}
},
{
"tool": "select_option",
"tags": [],
"reasons": {}
},
{
"tool": "ax_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "read_text",
"tags": [],
"reasons": {}
},
{
"tool": "run",
"tags": [],
"reasons": {}
},
{
"tool": "click_element",
"tags": [],
"reasons": {}
},
{
"tool": "get_template",
"tags": [],
"reasons": {}
},
{
"tool": "find_template",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for_visual",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "848916b9c88d4c07b58176bcb467842b54b0decfc9563b541c1729ccdcaae0cc",
"stats": {
"tools": 48,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 0,
"low": 0,
"info": 0
}
}
}