Local Delegate — 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": "local-delegate-mcp",
"source": {
"kind": "package",
"origin": "local-delegate-mcp"
},
"server": {
"name": "local-delegate-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": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/local_delegate/autostart.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/local_delegate/autostart.py:72`): 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/local_delegate/autostart.py"
},
"evidence": "try: subprocess.Popen( args, creationflags=flags, std",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/local_delegate/autostart.py",
"line": 72,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/local_delegate/doctor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/local_delegate/doctor.py:67`): 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/local_delegate/doctor.py"
},
"evidence": "try: out = subprocess.run( [exe, \"--version\"], capture_output=True, tex",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/local_delegate/doctor.py",
"line": 67,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/local_delegate/install.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/local_delegate/install.py:926`): 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/local_delegate/install.py"
},
"evidence": "try: subprocess.run( [\"claude\", \"mcp\", \"remove\", \"--scope\", \"user\", SERVER_NAME],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/local_delegate/install.py",
"line": 926,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/local_delegate/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/local_delegate/server.py:1924`): 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/local_delegate/server.py"
},
"evidence": "try: out = subprocess.run( [\"nvidia-smi\", \"--query-gpu=memory.used,memory.total\", \"--format=cs",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/local_delegate/server.py",
"line": 1924,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/local_delegate/update.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/local_delegate/update.py:68`): 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/local_delegate/update.py"
},
"evidence": "try: return subprocess.run(argv, capture_output=True, text=True, timeout=30) except (OSError, subprocess",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/local_delegate/update.py",
"line": 68,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/local_delegate/web/sysinfo.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/local_delegate/web/sysinfo.py:78`): 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/local_delegate/web/sysinfo.py"
},
"evidence": "try: out = subprocess.run( [ \"nvidia-smi\", \"--query-gpu=memory.",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/local_delegate/web/sysinfo.py",
"line": 78,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_core.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_core.py:725`): 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": "tests/test_core.py"
},
"evidence": "odules))\" ) r = subprocess.run( [sys.executable, \"-c\", code], capture_output=True, text=True, timeout=60",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_core.py",
"line": 725,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_ctrl_c.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_ctrl_c.py:187`): 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": "tests/test_ctrl_c.py"
},
"evidence": "o. \"\"\" return subprocess.Popen( [sys.executable, \"-m\", \"local_delegate\", *args], env=env,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_ctrl_c.py",
"line": 187,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_dashboard_js.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_dashboard_js.py:66`): 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": "tests/test_dashboard_js.py"
},
"evidence": "TZ_PRUEBA} salida = subprocess.run( [node, str(programa)], capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_dashboard_js.py",
"line": 66,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_hooks_telemetry_api.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_hooks_telemetry_api.py:259`): 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": "tests/test_hooks_telemetry_api.py"
},
"evidence": "-8\", ) salida = subprocess.run( [node, str(programa)], capture_output=True, text=True, timeout=30, check",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_hooks_telemetry_api.py",
"line": 259,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"local-delegate-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "local-delegate-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "8a243595fe0edf58af5f6f35e9dd89f93f94ce5615c0ec432d71137670036a47",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 0,
"low": 4,
"info": 1
}
}
}