Puppeteer Linux — 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": "mcp-puppeteer-linux",
"source": {
"kind": "package",
"origin": "mcp-puppeteer-linux"
},
"server": {
"name": "mcp-puppeteer-linux"
}
},
"grade": "C",
"score": {
"score": 71,
"threatScore": 78,
"grade": "C",
"band": "C",
"categorySubtotals": {
"injection": 21.7,
"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": "threat",
"ruleId": "MTC-SRC-011",
"category": "injection",
"severity": "high",
"confidence": "strong",
"rawWeight": 22,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 15.4
},
{
"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 (7 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 (dist/index.js)",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:340`): 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": "dist/index.js"
},
"evidence": "const result = eval(script); Object.assign(console, originalConsole);",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-010",
"file": "dist/index.js",
"line": 340,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-011",
"title": "Assembled command execution and dynamic evaluation in the same server",
"category": "injection",
"severity": "high",
"confidence": "strong",
"description": "The implementation both builds shell commands out of runtime values (`dist/index.js`) and evaluates runtime values as code (`dist/index.js`). Each is a separate arbitrary-execution primitive; a server exposing both gives anything that reaches either one a direct path to running attacker-chosen code.",
"remediation": "Remove the dynamic eval, and pass command arguments as an argv array instead of building a shell string. If both are genuinely required, constrain and validate every value that can reach them.",
"location": {
"kind": "server",
"name": "dist/index.js"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rules": [
"MTC-SRC-009",
"MTC-SRC-010"
],
"commandFile": "dist/index.js",
"evalFile": "dist/index.js",
"sameFile": true
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"puppeteer_evaluate\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"puppeteer_evaluate\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "puppeteer_evaluate"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:340`): 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/index.js"
},
"evidence": "const result = eval(script); Object.assign(console, originalConsole);",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/index.js",
"line": 340,
"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:7`): 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'; // Function to detect X11 environment function getX11Environment() { if (pla",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/index.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:16`): 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/index.js"
},
"evidence": "let psOutput = execSync(`ps aux | grep -i \"kwin_x11\" | grep \"${username}\"`).toString(); let lines = psO",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/index.js",
"line": 16,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"puppeteer_evaluate\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"puppeteer_evaluate\" takes a command-shaped parameter \"script\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "puppeteer_evaluate",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"puppeteer_evaluate\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"puppeteer_evaluate\" 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": "puppeteer_evaluate"
},
"data": {
"tags": [
"code-exec"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "puppeteer_navigate",
"tags": [],
"reasons": {}
},
{
"tool": "puppeteer_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "puppeteer_click",
"tags": [],
"reasons": {}
},
{
"tool": "puppeteer_fill",
"tags": [],
"reasons": {}
},
{
"tool": "puppeteer_select",
"tags": [],
"reasons": {}
},
{
"tool": "puppeteer_hover",
"tags": [],
"reasons": {}
},
{
"tool": "puppeteer_evaluate",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
}
],
"surfaceDigest": "ce1f4780908eea0dd0914e80dd82d14ef9adb6a85d8da0cfa95a093dc2c0dd9a",
"stats": {
"tools": 7,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 2,
"low": 1,
"info": 0
}
}
}