Pilot — 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": "pilot-mcp",
"source": {
"kind": "package",
"origin": "pilot-mcp"
},
"server": {
"name": "pilot-mcp"
}
},
"grade": "A",
"score": {
"score": 92,
"threatScore": 99,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 1.2,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SUP-010",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"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 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 (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-010",
"title": "Dynamic evaluation of a non-literal value (extension/content.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`extension/content.js:334`): 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/content.js"
},
"evidence": "o-eval const result = eval(script); return { result: typeof result === 'object' ? JSON.stringify(result) : String(re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "extension/content.js",
"line": 334,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (extension/content.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`extension/content.js:334`): 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/content.js"
},
"evidence": "o-eval const result = eval(script); return { result: typeof result === 'object' ? JSON.stringify(result) : String(re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "extension/content.js",
"line": 334,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli/client.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli/client.js:26`): 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/client.js"
},
"evidence": "import { spawn } from 'child_process'; import { fileURLToPath } from 'url'; const SOCKET_PATH = path.join(os.tmpdir(),",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli/client.js",
"line": 26,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cookie-import.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cookie-import.js:15`): 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/cookie-import.js"
},
"evidence": "import { spawn } from 'child_process'; export class CookieImportError extends Error { code; action; constru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cookie-import.js",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:18`): 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/index.js"
},
"evidence": "port { execSync } from 'child_process'; import * as fs from 'fs'; import * as path from 'path'; import * as os from 'os'",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 18,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-010",
"title": "Package runs install-time scripts (postinstall)",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"description": "\"pilot-mcp\" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.",
"remediation": "Review the scripts; install with --ignore-scripts where possible and vet what they do.",
"location": {
"kind": "package",
"name": "pilot-mcp"
},
"evidence": "node scripts/postinstall.js",
"owasp": "LLM03:2025 Supply Chain",
"references": [
"https://github.com/ossf/package-analysis",
"https://owasp.org/www-project-top-10-ci-cd-security-risks/"
],
"data": {
"scripts": [
"postinstall"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "pilot_intercept",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_assert",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_clipboard",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_frames",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_frame_select",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_frame_reset",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_console",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_network",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_evaluate",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_cookies",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_storage",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_perf",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_click",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_hover",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_fill",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_select_option",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_type",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_press_key",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_drag",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_scroll",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_wait",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_file_upload",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_navigate",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_back",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_forward",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_reload",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_get",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_page_text",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_page_html",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_page_links",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_page_forms",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_page_attrs",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_page_css",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_element_state",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_resize",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_set_cookie",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_import_cookies",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_set_header",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_set_useragent",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_handle_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_extension_status",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_cdp",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_handoff",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_resume",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_close",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_auth",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_block",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_geolocation",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_snapshot_diff",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_find",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_annotated_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_tabs",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_tab_new",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_tab_close",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_tab_select",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_pdf",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_responsive",
"tags": [],
"reasons": {}
},
{
"tool": "pilot_page_diff",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "4bad699e8bb96c3d3a62aa3ac7d55c4af10dc62240c1d6f680a75228e0d7a8fc",
"stats": {
"tools": 61,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 1,
"info": 0
}
}
}