Firebase Tools — 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": "firebase-tools",
"source": {
"kind": "package",
"origin": "firebase-tools"
},
"server": {
"name": "firebase-tools"
}
},
"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 send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (lib/init/features/apphosting.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/init/features/apphosting.js:20`): 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": "lib/init/features/apphosting.js"
},
"evidence": "nst { dynamicImport } = eval(\"require\")(\"../../dynamicImport\"); const projectId = setup.projectId; if (!(await (",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "lib/init/features/apphosting.js",
"line": 20,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (lib/agentSkills.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/agentSkills.js:5`): 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": "lib/agentSkills.js"
},
"evidence": "stallAgentSkills; const child_process_1 = require(\"child_process\"); const utils = require(\"./utils\"); const prompt = req",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "lib/agentSkills.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (lib/emulator/commandUtils.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/emulator/commandUtils.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": "lib/emulator/commandUtils.js"
},
"evidence": "childProcess = require(\"child_process\"); const controller = require(\"../emulator/controller\"); const config_1 = require(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "lib/emulator/commandUtils.js",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (lib/emulator/dataconnectEmulator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/emulator/dataconnectEmulator.js:4`): 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": "lib/emulator/dataconnectEmulator.js"
},
"evidence": "childProcess = require(\"child_process\"); const pg = require(\"pg\"); const events_1 = require(\"events\"); const clc = requi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "lib/emulator/dataconnectEmulator.js",
"line": 4,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (lib/emulator/downloadableEmulators.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/emulator/downloadableEmulators.js:19`): 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": "lib/emulator/downloadableEmulators.js"
},
"evidence": "childProcess = require(\"child_process\"); const utils = require(\"../utils\"); const emulatorLogger_1 = require(\"./emulator",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "lib/emulator/downloadableEmulators.js",
"line": 19,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (lib/emulator/functionsEmulator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/emulator/functionsEmulator.js:1110`): 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": "lib/emulator/functionsEmulator.js"
},
"evidence": "const childProcess = spawn(bin, args, { cwd: backend.functionsDir, env: { nod",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "lib/emulator/functionsEmulator.js",
"line": 1110,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (lib/init/features/dataconnect/create_app.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/init/features/dataconnect/create_app.js:36`): 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": "lib/init/features/dataconnect/create_app.js"
},
"evidence": "const childProcess = spawn(command, args, { stdio: \"inherit\", }); childProcess.on(\"close\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "lib/init/features/dataconnect/create_app.js",
"line": 36,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (lib/init/features/functions/dart.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`lib/init/features/functions/dart.js:24`): 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": "lib/init/features/functions/dart.js"
},
"evidence": "const installProcess = spawn(\"dart\", [\"pub\", \"get\"], { cwd: config.path(setup.functions.source),",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "lib/init/features/functions/dart.js",
"line": 24,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (standalone/firepit.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`standalone/firepit.js:71`): 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": "standalone/firepit.js"
},
"evidence": "ork, spawn } = require(\"child_process\"); const homePath = require(\"user-home\"); const chalk = require(\"chalk\"); const sh",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "standalone/firepit.js",
"line": 71,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (lib/mcp/resources/docs.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`lib/mcp/resources/docs.js:14`): 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": "lib/mcp/resources/docs.js"
},
"evidence": "const response = await fetch(`https://firebase.google.com/docs/${path}.md.txt`); if (response.status >= 400) {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "lib/mcp/resources/docs.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (lib/dynamicImport.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`lib/dynamicImport.js:14`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "lib/dynamicImport.js"
},
"evidence": "With(\"file://\")) return import(mod); if (mod.startsWith(\"/\")) return import(pathToFileURL(mod).toString()); try",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "lib/dynamicImport.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (lib/emulator/functionsEmulatorRuntime.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`lib/emulator/functionsEmulatorRuntime.js:19`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "lib/emulator/functionsEmulatorRuntime.js"
},
"evidence": "n(\"modulePath\", \"return import(modulePath)\"); function noOp() { return false; } function requireAsync(moduleName, op",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "lib/emulator/functionsEmulatorRuntime.js",
"line": 19,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "ce0cb9f03030753dec54ada360095a639a7d034d164e709764660a470fdbcf1f",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 9,
"medium": 3,
"low": 0,
"info": 0
}
}
}