Packet Tracer — 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": "packet-tracer-mcp",
"source": {
"kind": "package",
"origin": "packet-tracer-mcp"
},
"server": {
"name": "packet-tracer-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 send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"external-sink",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (61 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 (EXTENSION/script-engine/main.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`EXTENSION/script-engine/main.js:137`): 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": "EXTENSION/script-engine/main.js"
},
"evidence": "; }; try { (new Function(\"reportResult\", js))(report); } catch (e) { captured = \"PT_ERROR: \" + e",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "EXTENSION/script-engine/main.js",
"line": 137,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/packet_tracer_mcp/infrastructure/execution/bridge_token.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/packet_tracer_mcp/infrastructure/execution/bridge_token.py:6`): 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": "src/packet_tracer_mcp/infrastructure/execution/bridge_token.py"
},
"evidence": "ipt que PT ejecuta con `new Function()`. Bindear a 127.0.0.1 no impide que la petición se envíe — solo impide leer la re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/packet_tracer_mcp/infrastructure/execution/bridge_token.py",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/packet_tracer_mcp/infrastructure/execution/live_bridge.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/packet_tracer_mcp/infrastructure/execution/live_bridge.py:12`): 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": "src/packet_tracer_mcp/infrastructure/execution/live_bridge.py"
},
"evidence": "ever it finds there via new Function(). The token is what closes that; see bridge_token.py. The extension gets the toke",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/packet_tracer_mcp/infrastructure/execution/live_bridge.py",
"line": 12,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/packet_tracer_mcp/infrastructure/execution/deploy_executor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/packet_tracer_mcp/infrastructure/execution/deploy_executor.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": "src/packet_tracer_mcp/infrastructure/execution/deploy_executor.py"
},
"evidence": "False try: subprocess.run( \"clip\", input=text.encode(\"utf-16-le\"), chec",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/packet_tracer_mcp/infrastructure/execution/deploy_executor.py",
"line": 24,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/test_bridge_token.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_bridge_token.py:6`): 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": "tests/test_bridge_token.py"
},
"evidence": "JS que PT ejecuta con `new Function()`. Lo unico que cierra ese agujero es este secreto. Y no tenia un solo test. `gre",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/test_bridge_token.py",
"line": 6,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_bridge_security.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_bridge_security.py:275`): 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_bridge_security.py"
},
"evidence": "\"\"\" ) out = subprocess.run( [_sys.executable, \"-c\", code], capture_output=True, text=True, timeout=6",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_bridge_security.py",
"line": 275,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"packet-tracer-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "packet-tracer-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "pt_list_devices",
"tags": [],
"reasons": {}
},
{
"tool": "pt_list_templates",
"tags": [],
"reasons": {}
},
{
"tool": "pt_get_device_details",
"tags": [],
"reasons": {}
},
{
"tool": "pt_estimate_plan",
"tags": [],
"reasons": {}
},
{
"tool": "pt_plan_topology",
"tags": [],
"reasons": {}
},
{
"tool": "pt_validate_plan",
"tags": [],
"reasons": {}
},
{
"tool": "pt_fix_plan",
"tags": [],
"reasons": {}
},
{
"tool": "pt_explain_plan",
"tags": [],
"reasons": {}
},
{
"tool": "pt_generate_script",
"tags": [],
"reasons": {}
},
{
"tool": "pt_generate_configs",
"tags": [],
"reasons": {}
},
{
"tool": "pt_full_build",
"tags": [],
"reasons": {}
},
{
"tool": "pt_export",
"tags": [],
"reasons": {}
},
{
"tool": "pt_deploy",
"tags": [],
"reasons": {}
},
{
"tool": "pt_list_projects",
"tags": [],
"reasons": {}
},
{
"tool": "pt_load_project",
"tags": [],
"reasons": {}
},
{
"tool": "pt_live_deploy",
"tags": [],
"reasons": {}
},
{
"tool": "pt_bridge_status",
"tags": [],
"reasons": {}
},
{
"tool": "pt_verify_connectivity",
"tags": [],
"reasons": {}
},
{
"tool": "pt_save_project",
"tags": [],
"reasons": {}
},
{
"tool": "pt_open_project",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"open_pr\""
]
}
},
{
"tool": "pt_query_topology",
"tags": [],
"reasons": {}
},
{
"tool": "pt_export_topology",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"export_to\""
]
}
},
{
"tool": "pt_delete_device",
"tags": [],
"reasons": {}
},
{
"tool": "pt_rename_device",
"tags": [],
"reasons": {}
},
{
"tool": "pt_move_device",
"tags": [],
"reasons": {}
},
{
"tool": "pt_delete_link",
"tags": [],
"reasons": {}
},
{
"tool": "pt_add_device",
"tags": [],
"reasons": {}
},
{
"tool": "pt_add_link",
"tags": [],
"reasons": {}
},
{
"tool": "pt_set_port",
"tags": [],
"reasons": {}
},
{
"tool": "pt_send_raw",
"tags": [],
"reasons": {}
},
{
"tool": "pt_list_modules",
"tags": [],
"reasons": {}
},
{
"tool": "pt_add_module",
"tags": [],
"reasons": {}
},
{
"tool": "pt_install_modules_batch",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_acl",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_acl_object",
"tags": [],
"reasons": {}
},
{
"tool": "pt_remove_acl_object",
"tags": [],
"reasons": {}
},
{
"tool": "pt_remove_acl",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_nat",
"tags": [],
"reasons": {}
},
{
"tool": "pt_remove_nat",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_vlan",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_stp",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_port_security",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_hardening",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_interface_tuning",
"tags": [],
"reasons": {}
},
{
"tool": "pt_diff",
"tags": [],
"reasons": {}
},
{
"tool": "pt_health_check",
"tags": [],
"reasons": {}
},
{
"tool": "pt_audit_security",
"tags": [],
"reasons": {}
},
{
"tool": "pt_inspect_ports",
"tags": [],
"reasons": {}
},
{
"tool": "pt_read_vlans",
"tags": [],
"reasons": {}
},
{
"tool": "pt_device_power",
"tags": [],
"reasons": {}
},
{
"tool": "pt_simulation_mode",
"tags": [],
"reasons": {}
},
{
"tool": "pt_simulation_step",
"tags": [],
"reasons": {}
},
{
"tool": "pt_read_packet_trace",
"tags": [],
"reasons": {}
},
{
"tool": "pt_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "pt_add_note",
"tags": [],
"reasons": {}
},
{
"tool": "pt_clear_annotations",
"tags": [],
"reasons": {}
},
{
"tool": "pt_backup_config",
"tags": [],
"reasons": {}
},
{
"tool": "pt_project_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "pt_workspace_options",
"tags": [],
"reasons": {}
},
{
"tool": "pt_apply_netflow",
"tags": [],
"reasons": {}
},
{
"tool": "pt_read_qos",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "caf1bbd7fe81f5eee85cc734e284fdeb65dca0a9d4aac0fc7a9f1cda06e0fc46",
"stats": {
"tools": 61,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 2,
"info": 1
}
}
}