Proxy — 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": "proxy-mcp",
"source": {
"kind": "package",
"origin": "proxy-mcp"
},
"server": {
"name": "proxy-mcp"
}
},
"grade": "B",
"score": {
"score": 86,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"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": [
"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 (89 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 \"interceptor_spawn\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"interceptor_spawn\" appears to run shell commands or evaluate code (keyword \"spawn\" 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": "interceptor_spawn"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"external-sink",
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/interceptors/android-adb.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/interceptors/android-adb.js:11`): 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": "dist/interceptors/android-adb.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import { pemToDer, getSubjectHash } from",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/interceptors/android-adb.js",
"line": 11,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/interceptors/android-frida.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/interceptors/android-frida.js: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": "dist/interceptors/android-frida.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import { buildFridaBundle } from \"../frid",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/interceptors/android-frida.js",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/interceptors/camoufox.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/interceptors/camoufox.js:25`): 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": "dist/interceptors/camoufox.js"
},
"evidence": "spawnSync } from \"node:child_process\"; import { mkdtemp, writeFile, rm, access, readFile } from \"node:fs/promises\"; imp",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/interceptors/camoufox.js",
"line": 25,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/interceptors/docker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/interceptors/docker.js:52`): 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": "dist/interceptors/docker.js"
},
"evidence": "} = await import(\"node:child_process\"); execSync(`docker cp \"${certPath}\" ${containerId}:/tmp/proxy-mcp-ca.",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/interceptors/docker.js",
"line": 52,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/interceptors/terminal.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/interceptors/terminal.js:8`): 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": "dist/interceptors/terminal.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { writeCertTempFile } from \"./cert-utils.js\"; const MAX_OUTPUT_BUFFER = 8",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/interceptors/terminal.js",
"line": 8,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/interceptors/docker.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/interceptors/docker.js:53`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "dist/interceptors/docker.js"
},
"evidence": "_process\"); execSync(`docker cp \"${certPath}\" ${containerId}:/tmp/proxy-mcp-ca.pem`, { timeout: 10000 });",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/interceptors/docker.js",
"line": 53,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"interceptor_spawn\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"interceptor_spawn\" 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": "interceptor_spawn"
},
"data": {
"tags": [
"external-sink",
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"proxy-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "proxy-mcp"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"proxy-mcp\" 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": "proxy-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "interceptor_camoufox_launch",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_camoufox_info",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_camoufox_list",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_camoufox_close",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_list_console",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_list_cookies",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_get_cookie",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_list_storage_keys",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_get_storage_value",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_list_network_fields",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_get_network_field",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_evaluate",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_inject_init_script",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_add_script_tag",
"tags": [],
"reasons": {}
},
{
"tool": "humanizer_move",
"tags": [],
"reasons": {}
},
{
"tool": "humanizer_click",
"tags": [],
"reasons": {}
},
{
"tool": "humanizer_type",
"tags": [],
"reasons": {}
},
{
"tool": "humanizer_scroll",
"tags": [],
"reasons": {}
},
{
"tool": "humanizer_idle",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_list",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_status",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_deactivate_all",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_launch",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_navigate",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_browser_close",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_spawn",
"tags": [
"external-sink",
"code-exec"
],
"reasons": {
"external-sink": [
"keyword \"curl\""
],
"code-exec": [
"keyword \"spawn\" in tool name"
]
}
},
{
"tool": "interceptor_kill",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_android_devices",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_android_activate",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_android_deactivate",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_android_setup",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_frida_apps",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_frida_attach",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_frida_detach",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_docker_attach",
"tags": [],
"reasons": {}
},
{
"tool": "interceptor_docker_detach",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_start",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_stop",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_status",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_get_ca_cert",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_mobile_setup",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_mobile_teardown",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_mobile_detect_iface",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_inject_headers",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_rewrite_url",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_mock_response",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_add_rule",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_update_rule",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_remove_rule",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_list_rules",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_test_rule_match",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_enable_rule",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_disable_rule",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_session_start",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_session_stop",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_session_status",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_list_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_get_session",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_import_har",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_query_session",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_search_session_bodies",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"http_request\""
]
}
},
{
"tool": "proxy_get_session_handshakes",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_get_session_exchange",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_replay_session",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_export_har",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_delete_session",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_session_recover",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_get_tls_fingerprints",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_list_tls_fingerprints",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_set_ja3_spoof",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_set_fingerprint_spoof",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_list_fingerprint_presets",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_check_fingerprint_runtime",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_clear_ja3_spoof",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_get_tls_config",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_enable_server_tls_capture",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_list_traffic",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_get_exchange",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_search_traffic",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_clear_traffic",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_start_transparent",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_stop_transparent",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_transparent_status",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_set_upstream",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_clear_upstream",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_set_host_upstream",
"tags": [],
"reasons": {}
},
{
"tool": "proxy_remove_host_upstream",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c1a7274d9193384f5c62c5d1813e73df8e0d8b5ee7f40b221c139903c25a8962",
"stats": {
"tools": 89,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 1,
"low": 1,
"info": 2
}
}
}