Ziniao — 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": "ziniao",
"source": {
"kind": "package",
"origin": "ziniao"
},
"server": {
"name": "ziniao"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"external-sink",
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (35 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-001",
"title": "Dynamic code execution in server code (ziniao_mcp/cli/dispatch.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ziniao_mcp/cli/dispatch.py:1307`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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": "ziniao_mcp/cli/dispatch.py"
},
"evidence": "= await Promise.resolve(eval(inj.expression)); }} catch(e) {{}} }} if (val != null) {{ h[inj.header] =",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "ziniao_mcp/cli/dispatch.py",
"line": 1307,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (ziniao_mcp/flows/runner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ziniao_mcp/flows/runner.py:346`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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": "ziniao_mcp/flows/runner.py"
},
"evidence": "Any] = {} exec(compile(wrapped, \"<flow_code>\", \"exec\"), g, loc) # noqa: S102 return loc.get(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "ziniao_mcp/flows/runner.py",
"line": 346,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (ziniao_mcp/chrome_passive.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ziniao_mcp/chrome_passive.py:161`): 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": "ziniao_mcp/chrome_passive.py"
},
"evidence": ", ) process = subprocess.Popen( # pylint: disable=consider-using-with args, stdout=subproce",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "ziniao_mcp/chrome_passive.py",
"line": 161,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (ziniao_mcp/cli/commands/lifecycle.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ziniao_mcp/cli/commands/lifecycle.py:24`): 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": "ziniao_mcp/cli/commands/lifecycle.py"
},
"evidence": "try: result = subprocess.run( [\"tasklist\", \"/FI\", \"IMAGENAME eq ziniao.exe\", \"/FO\", \"CSV\", \"/NH\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "ziniao_mcp/cli/commands/lifecycle.py",
"line": 24,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (ziniao_mcp/cli/commands/skill_cmd.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ziniao_mcp/cli/commands/skill_cmd.py:95`): 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": "ziniao_mcp/cli/commands/skill_cmd.py"
},
"evidence": "port subprocess subprocess.run( [\"cmd\", \"/c\", \"mklink\", \"/J\", str(target_dir), str(source_dir)],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "ziniao_mcp/cli/commands/skill_cmd.py",
"line": 95,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (ziniao_mcp/cli/commands/update_cmd.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ziniao_mcp/cli/commands/update_cmd.py:88`): 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": "ziniao_mcp/cli/commands/update_cmd.py"
},
"evidence": "try: proc = subprocess.run( [uv_exe, \"tool\", \"dir\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "ziniao_mcp/cli/commands/update_cmd.py",
"line": 88,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (ziniao_mcp/cli/connection.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`ziniao_mcp/cli/connection.py:91`): 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": "ziniao_mcp/cli/connection.py"
},
"evidence": "ETACHED_PROCESS subprocess.Popen( # pylint: disable=consider-using-with [exe, \"-m\", daemon_module],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "ziniao_mcp/cli/connection.py",
"line": 91,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([network_unroute, page_fetch]) co-exist with external-action tools ([upload_file, har_stop]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow",
"name": "network_unroute → upload_file"
},
"evidence": "untrusted [network_unroute, page_fetch] → sinks [upload_file, har_stop]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"network_unroute",
"page_fetch"
],
"sinks": [
"upload_file",
"har_stop"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/cli_test_all.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/cli_test_all.py:23`): 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": "scripts/cli_test_all.py"
},
"evidence": "try: r = subprocess.run( cmd, cwd=ROOT, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/cli_test_all.py",
"line": 23,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/e2e_cookie_vault_isolated_restore.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/e2e_cookie_vault_isolated_restore.py:49`): 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": "scripts/e2e_cookie_vault_isolated_restore.py"
},
"evidence": "cmd += argv proc = subprocess.run( cmd, cwd=ROOT, capture_output=True, text=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/e2e_cookie_vault_isolated_restore.py",
"line": 49,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/rakuten_presets_smoke.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/rakuten_presets_smoke.py:30`): 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": "scripts/rakuten_presets_smoke.py"
},
"evidence": "try: p = subprocess.run( cmd, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/rakuten_presets_smoke.py",
"line": 30,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/test_minimal_env.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/test_minimal_env.py:42`): 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": "scripts/test_minimal_env.py"
},
"evidence": "}\", flush=True) proc = subprocess.Popen( # pylint: disable=consider-using-with cmd, stdin=subprocess.PIPE,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/test_minimal_env.py",
"line": 42,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_skill_junction_windows.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_skill_junction_windows.py:22`): 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_skill_junction_windows.py"
},
"evidence": "\"site-development\" subprocess.run( [\"cmd\", \"/c\", \"mklink\", \"/J\", str(link), str(old_target)], che",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_skill_junction_windows.py",
"line": 22,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"ziniao\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "ziniao"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"network_unroute",
"page_fetch"
],
"sensitiveSource": [],
"externalSink": [
"upload_file",
"har_stop"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "launch_chrome",
"tags": [],
"reasons": {}
},
{
"tool": "connect_chrome",
"tags": [],
"reasons": {}
},
{
"tool": "list_chrome",
"tags": [],
"reasons": {}
},
{
"tool": "close_chrome",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate_script",
"tags": [],
"reasons": {}
},
{
"tool": "take_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "take_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "console",
"tags": [],
"reasons": {}
},
{
"tool": "emulate",
"tags": [],
"reasons": {}
},
{
"tool": "click",
"tags": [],
"reasons": {}
},
{
"tool": "fill",
"tags": [],
"reasons": {}
},
{
"tool": "type_text",
"tags": [],
"reasons": {}
},
{
"tool": "press_key",
"tags": [],
"reasons": {}
},
{
"tool": "hover",
"tags": [],
"reasons": {}
},
{
"tool": "drag",
"tags": [],
"reasons": {}
},
{
"tool": "handle_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "upload_file",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "navigate_page",
"tags": [],
"reasons": {}
},
{
"tool": "tab",
"tags": [],
"reasons": {}
},
{
"tool": "switch_frame",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for",
"tags": [],
"reasons": {}
},
{
"tool": "network",
"tags": [],
"reasons": {}
},
{
"tool": "network_route",
"tags": [],
"reasons": {}
},
{
"tool": "network_unroute",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "network_routes",
"tags": [],
"reasons": {}
},
{
"tool": "har_start",
"tags": [],
"reasons": {}
},
{
"tool": "har_stop",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"export_to\""
]
}
},
{
"tool": "page_fetch",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "recorder",
"tags": [],
"reasons": {}
},
{
"tool": "browser_session",
"tags": [],
"reasons": {}
},
{
"tool": "start_client",
"tags": [],
"reasons": {}
},
{
"tool": "list_stores",
"tags": [],
"reasons": {}
},
{
"tool": "open_store",
"tags": [],
"reasons": {}
},
{
"tool": "close_store",
"tags": [],
"reasons": {}
},
{
"tool": "stop_client",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "43181a7d787af73e948b8ca42f2169fdceda48b7668e2fef5d8408a61b7b56f3",
"stats": {
"tools": 35,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 1,
"low": 5,
"info": 1
}
}
}