Playwriter Browser — 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": "playwriter-browser-mcp",
"source": {
"kind": "package",
"origin": "playwriter-browser-mcp"
},
"server": {
"name": "playwriter-browser-mcp"
}
},
"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": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (38 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 \"browser_run_code\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"browser_run_code\" appears to run shell commands or evaluate code (keyword \"run_code\" 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": "browser_run_code"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/tools/run-code.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/run-code.js:11`): 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": "dist/tools/run-code.js"
},
"evidence": "const fn = new Function(\"page\", `return (${code})(page);`); const result = await fn(page);",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/tools/run-code.js",
"line": 11,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/tools/run-code.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tools/run-code.ts:22`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/tools/run-code.ts"
},
"evidence": "eval const fn = new Function(\"page\", `return (${code})(page);`); const result: unknown = await (fn as Fu",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/tools/run-code.ts",
"line": 22,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/browser/connection.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/browser/connection.js:3`): 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/browser/connection.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import net from \"node:net\"; import { BrowserState } from \"./state.js\"; const CON",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/browser/connection.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/browser/connection.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/browser/connection.ts:3`): 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/browser/connection.ts"
},
"evidence": "{ execFile } from \"node:child_process\"; import net from \"node:net\"; import type { Config } from \"../config.js\"; import {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/browser/connection.ts",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"browser_run_code\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"browser_run_code\" 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": "browser_run_code"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/tools/install.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/tools/install.js:1`): 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/tools/install.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { textResult, errorResult } from \"../utils/result.js\"; export function re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/tools/install.js",
"line": 1,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"playwriter-browser-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "playwriter-browser-mcp"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"playwriter-browser-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": "playwriter-browser-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "browser_click",
"tags": [],
"reasons": {}
},
{
"tool": "browser_close",
"tags": [],
"reasons": {}
},
{
"tool": "browser_console_messages",
"tags": [],
"reasons": {}
},
{
"tool": "browser_handle_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "browser_drag",
"tags": [],
"reasons": {}
},
{
"tool": "browser_evaluate",
"tags": [],
"reasons": {}
},
{
"tool": "browser_file_upload",
"tags": [],
"reasons": {}
},
{
"tool": "browser_fill_form",
"tags": [],
"reasons": {}
},
{
"tool": "browser_hover",
"tags": [],
"reasons": {}
},
{
"tool": "browser_install",
"tags": [],
"reasons": {}
},
{
"tool": "browser_press_key",
"tags": [],
"reasons": {}
},
{
"tool": "browser_navigate",
"tags": [],
"reasons": {}
},
{
"tool": "browser_navigate_back",
"tags": [],
"reasons": {}
},
{
"tool": "browser_network_requests",
"tags": [],
"reasons": {}
},
{
"tool": "browser_pdf_save",
"tags": [],
"reasons": {}
},
{
"tool": "browser_reset",
"tags": [],
"reasons": {}
},
{
"tool": "browser_resize",
"tags": [],
"reasons": {}
},
{
"tool": "browser_run_code",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_code\" in tool name"
]
}
},
{
"tool": "browser_take_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "browser_select_option",
"tags": [],
"reasons": {}
},
{
"tool": "browser_session",
"tags": [],
"reasons": {}
},
{
"tool": "browser_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "browser_tabs",
"tags": [],
"reasons": {}
},
{
"tool": "browser_generate_locator",
"tags": [],
"reasons": {}
},
{
"tool": "browser_verify_element_visible",
"tags": [],
"reasons": {}
},
{
"tool": "browser_verify_text_visible",
"tags": [],
"reasons": {}
},
{
"tool": "browser_verify_list_visible",
"tags": [],
"reasons": {}
},
{
"tool": "browser_verify_value",
"tags": [],
"reasons": {}
},
{
"tool": "browser_start_tracing",
"tags": [],
"reasons": {}
},
{
"tool": "browser_stop_tracing",
"tags": [],
"reasons": {}
},
{
"tool": "browser_type",
"tags": [],
"reasons": {}
},
{
"tool": "browser_mouse_move_xy",
"tags": [],
"reasons": {}
},
{
"tool": "browser_mouse_click_xy",
"tags": [],
"reasons": {}
},
{
"tool": "browser_mouse_drag_xy",
"tags": [],
"reasons": {}
},
{
"tool": "browser_mouse_down",
"tags": [],
"reasons": {}
},
{
"tool": "browser_mouse_up",
"tags": [],
"reasons": {}
},
{
"tool": "browser_mouse_wheel",
"tags": [],
"reasons": {}
},
{
"tool": "browser_wait_for",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "4e19e76463248dd6d107943b1a3ae02834daf7ffe43598e34176fcb72eaa705c",
"stats": {
"tools": 38,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 2,
"info": 2
}
}
}