Chrome Bridge — 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": "chrome-bridge-mcp",
"source": {
"kind": "package",
"origin": "chrome-bridge-mcp"
},
"server": {
"name": "chrome-bridge-mcp"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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": [
"untrusted-input",
"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 (59 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-010",
"title": "Dynamic evaluation of a non-literal value (extension/service-worker.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`extension/service-worker.js:560`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate 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/service-worker.js"
},
"evidence": "ch { try { fn = new Function(userCode); } catch (e) { return { ok: false, error: String(e?.message ||",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "extension/service-worker.js",
"line": 560,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (extension/service-worker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`extension/service-worker.js:558`): 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/service-worker.js"
},
"evidence": "try { fn = new Function(`return (${userCode});`); } catch { try { fn = new Function(userCode)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "extension/service-worker.js",
"line": 558,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (server/launcher.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`server/launcher.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": "server/launcher.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { cp, mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises'; import { e",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "server/launcher.js",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([get_page_info, monitor_network]) co-exist with external-action tools ([upload_file, http_request]). 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": "get_page_info → upload_file"
},
"evidence": "untrusted [get_page_info, monitor_network] → sinks [upload_file, http_request]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"get_page_info",
"monitor_network"
],
"sinks": [
"upload_file",
"http_request"
]
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tools/cws-upload.mjs)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tools/cws-upload.mjs:115`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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": "tools/cws-upload.mjs"
},
"evidence": ") { const res = await fetch('https://oauth2.googleapis.com/token', { method: 'POST', headers: { 'Content-Type'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tools/cws-upload.mjs",
"line": 115,
"nonRuntime": true
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"get_page_info",
"monitor_network"
],
"sensitiveSource": [],
"externalSink": [
"upload_file",
"http_request"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "get_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_tabs",
"tags": [],
"reasons": {}
},
{
"tool": "navigate",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "execute_js",
"tags": [],
"reasons": {}
},
{
"tool": "click",
"tags": [],
"reasons": {}
},
{
"tool": "type_text",
"tags": [],
"reasons": {}
},
{
"tool": "read_page",
"tags": [],
"reasons": {}
},
{
"tool": "get_page_info",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "get_storage",
"tags": [],
"reasons": {}
},
{
"tool": "query_dom",
"tags": [],
"reasons": {}
},
{
"tool": "modify_dom",
"tags": [],
"reasons": {}
},
{
"tool": "inject_css",
"tags": [],
"reasons": {}
},
{
"tool": "read_console",
"tags": [],
"reasons": {}
},
{
"tool": "monitor_network",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "create_tab",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for",
"tags": [],
"reasons": {}
},
{
"tool": "scroll",
"tags": [],
"reasons": {}
},
{
"tool": "set_storage",
"tags": [],
"reasons": {}
},
{
"tool": "fill_form",
"tags": [],
"reasons": {}
},
{
"tool": "viewport_resize",
"tags": [],
"reasons": {}
},
{
"tool": "element_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "full_page_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "measure_spacing",
"tags": [],
"reasons": {}
},
{
"tool": "watch_dom",
"tags": [],
"reasons": {}
},
{
"tool": "emulate_media",
"tags": [],
"reasons": {}
},
{
"tool": "hover",
"tags": [],
"reasons": {}
},
{
"tool": "press_key",
"tags": [],
"reasons": {}
},
{
"tool": "get_frames",
"tags": [],
"reasons": {}
},
{
"tool": "tab_action",
"tags": [],
"reasons": {}
},
{
"tool": "upload_file",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "dismiss_overlays",
"tags": [],
"reasons": {}
},
{
"tool": "handle_dialogs",
"tags": [],
"reasons": {}
},
{
"tool": "find_text",
"tags": [],
"reasons": {}
},
{
"tool": "network_rules",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot_diff",
"tags": [],
"reasons": {}
},
{
"tool": "track_events",
"tags": [],
"reasons": {}
},
{
"tool": "cookie_audit",
"tags": [],
"reasons": {}
},
{
"tool": "handoff",
"tags": [],
"reasons": {}
},
{
"tool": "watch",
"tags": [],
"reasons": {}
},
{
"tool": "read_form",
"tags": [],
"reasons": {}
},
{
"tool": "audit",
"tags": [],
"reasons": {}
},
{
"tool": "find_setting",
"tags": [],
"reasons": {}
},
{
"tool": "extract_table",
"tags": [],
"reasons": {}
},
{
"tool": "drag_and_drop",
"tags": [],
"reasons": {}
},
{
"tool": "clipboard",
"tags": [],
"reasons": {}
},
{
"tool": "set_geolocation",
"tags": [],
"reasons": {}
},
{
"tool": "manage_downloads",
"tags": [],
"reasons": {}
},
{
"tool": "save_page",
"tags": [],
"reasons": {}
},
{
"tool": "http_request",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"http_request\""
]
}
},
{
"tool": "move_tab",
"tags": [],
"reasons": {}
},
{
"tool": "tile_windows",
"tags": [],
"reasons": {}
},
{
"tool": "window_layout",
"tags": [],
"reasons": {}
},
{
"tool": "http_auth",
"tags": [],
"reasons": {}
},
{
"tool": "session_fixture",
"tags": [],
"reasons": {}
},
{
"tool": "get_interactives",
"tags": [],
"reasons": {}
},
{
"tool": "extract",
"tags": [],
"reasons": {}
},
{
"tool": "assert",
"tags": [],
"reasons": {}
},
{
"tool": "session_record",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "1306a9b704a618319d6d8486e638879347ac4b4152ab5b5b008f5a2bf294954e",
"stats": {
"tools": 59,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 1,
"low": 1,
"info": 0
}
}
}