Claude Chrome Parallel — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "claude-chrome-parallel",
"source": {
"kind": "package",
"origin": "claude-chrome-parallel"
},
"server": {
"name": "claude-chrome-parallel"
}
},
"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-1.9"
},
"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 (47 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-002",
"title": "Shell/command execution in server code (dist/chrome/launcher.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/chrome/launcher.js:41`): 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/chrome/launcher.js"
},
"evidence": "etChromeLauncher; const child_process_1 = require(\"child_process\"); const path = __importStar(require(\"path\")); const fs",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/chrome/launcher.js",
"line": 41,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/claude-session.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/claude-session.js: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": "dist/cli/claude-session.js"
},
"evidence": "r(require(\"os\")); const child_process_1 = require(\"child_process\"); const BASE_DIR = path.join(os.homedir(), '.claude-ch",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/claude-session.js",
"line": 49,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/index.js:56`): 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/cli/index.js"
},
"evidence": "r(require(\"os\")); const child_process_1 = require(\"child_process\"); const update_check_1 = require(\"./update-check\"); co",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/index.js",
"line": 56,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/uninstall.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/uninstall.js:43`): 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/cli/uninstall.js"
},
"evidence": "r(require(\"os\")); const child_process_1 = require(\"child_process\"); /** * Get the installation directory */ function g",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/uninstall.js",
"line": 43,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/lightpanda/launcher.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/lightpanda/launcher.js:40`): 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/lightpanda/launcher.js"
},
"evidence": "auncher = void 0; const child_process_1 = require(\"child_process\"); const puppeteer = __importStar(require(\"puppeteer-co",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/lightpanda/launcher.js",
"line": 40,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/cli/install.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/cli/install.js:44`): 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/cli/install.js"
},
"evidence": "r(require(\"os\")); const child_process_1 = require(\"child_process\"); /** * Get the installation directory */ function g",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/install.js",
"line": 44,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "batch_execute",
"tags": [],
"reasons": {}
},
{
"tool": "click_element",
"tags": [],
"reasons": {}
},
{
"tool": "computer",
"tags": [],
"reasons": {}
},
{
"tool": "console_capture",
"tags": [],
"reasons": {}
},
{
"tool": "cookies",
"tags": [],
"reasons": {}
},
{
"tool": "drag_drop",
"tags": [],
"reasons": {}
},
{
"tool": "emulate_device",
"tags": [],
"reasons": {}
},
{
"tool": "file_upload",
"tags": [],
"reasons": {}
},
{
"tool": "fill_form",
"tags": [],
"reasons": {}
},
{
"tool": "find",
"tags": [],
"reasons": {}
},
{
"tool": "form_input",
"tags": [],
"reasons": {}
},
{
"tool": "geolocation",
"tags": [],
"reasons": {}
},
{
"tool": "http_auth",
"tags": [],
"reasons": {}
},
{
"tool": "javascript_tool",
"tags": [],
"reasons": {}
},
{
"tool": "lightweight_scroll",
"tags": [],
"reasons": {}
},
{
"tool": "memory_record",
"tags": [],
"reasons": {}
},
{
"tool": "memory_query",
"tags": [],
"reasons": {}
},
{
"tool": "memory_validate",
"tags": [],
"reasons": {}
},
{
"tool": "navigate",
"tags": [],
"reasons": {}
},
{
"tool": "network",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_init",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_status",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_collect",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_collect_partial",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_cleanup",
"tags": [],
"reasons": {}
},
{
"tool": "worker_update",
"tags": [],
"reasons": {}
},
{
"tool": "worker_complete",
"tags": [],
"reasons": {}
},
{
"tool": "execute_plan",
"tags": [],
"reasons": {}
},
{
"tool": "page_content",
"tags": [],
"reasons": {}
},
{
"tool": "page_pdf",
"tags": [],
"reasons": {}
},
{
"tool": "page_reload",
"tags": [],
"reasons": {}
},
{
"tool": "performance_metrics",
"tags": [],
"reasons": {}
},
{
"tool": "read_page",
"tags": [],
"reasons": {}
},
{
"tool": "request_intercept",
"tags": [],
"reasons": {}
},
{
"tool": "selector_query",
"tags": [],
"reasons": {}
},
{
"tool": "ccp_stop",
"tags": [],
"reasons": {}
},
{
"tool": "storage",
"tags": [],
"reasons": {}
},
{
"tool": "tabs_close",
"tags": [],
"reasons": {}
},
{
"tool": "tabs_context_mcp",
"tags": [],
"reasons": {}
},
{
"tool": "tabs_create_mcp",
"tags": [],
"reasons": {}
},
{
"tool": "user_agent",
"tags": [],
"reasons": {}
},
{
"tool": "wait_and_click",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for",
"tags": [],
"reasons": {}
},
{
"tool": "worker_create",
"tags": [],
"reasons": {}
},
{
"tool": "worker_delete",
"tags": [],
"reasons": {}
},
{
"tool": "worker_list",
"tags": [],
"reasons": {}
},
{
"tool": "xpath_query",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "7151431df578b5fc1dcf1fec3523822d9fed71e993a87144cdb6f13a524c5e2b",
"stats": {
"tools": 47,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 1,
"info": 0
}
}
}