Notebooklm — 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": "@roomi-fields/notebooklm-mcp",
"source": {
"kind": "package",
"origin": "@roomi-fields/notebooklm-mcp"
},
"server": {
"name": "@roomi-fields/notebooklm-mcp"
}
},
"grade": "B",
"score": {
"score": 84,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"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": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"kind": "client",
"term": "verification-discount",
"level": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code",
"untrusted input can reach code execution"
],
"tags": [
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (26 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/http-wrapper.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/http-wrapper.js:10`): 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/http-wrapper.js"
},
"evidence": "port { execSync } from 'child_process'; import { readFileSync } from 'fs'; import { dirname, join } from 'path'; import",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/http-wrapper.js",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/http-wrapper.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/http-wrapper.js:1210`): 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/http-wrapper.js"
},
"evidence": "const output = execSync(`netstat -ano | findstr :${port} | findstr LISTENING`, { encoding: 'utf",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/http-wrapper.js",
"line": 1210,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"notebook_url\" on \"download_audio\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"download_audio\" takes a URL/host parameter \"notebook_url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "download_audio",
"field": "inputSchema.properties.notebook_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "notebook_url"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/index.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/index.js:602`): 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": "dist/index.js"
},
"evidence": "le) { await import(cliModule); // each CLI runs its own main() on import return; }",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/index.js",
"line": 602,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/check-skill-sync.mjs)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/check-skill-sync.mjs: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": "scripts/check-skill-sync.mjs"
},
"evidence": "ecFileSync } from 'node:child_process'; /** bundled skill dir -> canonical location in its standalone repo */ const SKI",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/check-skill-sync.mjs",
"line": 15,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "Notebook Library",
"tags": [],
"reasons": {}
},
{
"tool": "Notebook by ID",
"tags": [],
"reasons": {}
},
{
"tool": "ask_question",
"tags": [],
"reasons": {}
},
{
"tool": "list_notebooks",
"tags": [],
"reasons": {}
},
{
"tool": "get_notebook",
"tags": [],
"reasons": {}
},
{
"tool": "add_notebook",
"tags": [],
"reasons": {}
},
{
"tool": "auto_discover_notebook",
"tags": [],
"reasons": {}
},
{
"tool": "list_notebooks_from_nblm",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"scrape\""
]
}
},
{
"tool": "select_notebook",
"tags": [],
"reasons": {}
},
{
"tool": "update_notebook",
"tags": [],
"reasons": {}
},
{
"tool": "remove_notebook",
"tags": [],
"reasons": {}
},
{
"tool": "search_notebooks",
"tags": [],
"reasons": {}
},
{
"tool": "get_library_stats",
"tags": [],
"reasons": {}
},
{
"tool": "list_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "close_session",
"tags": [],
"reasons": {}
},
{
"tool": "reset_session",
"tags": [],
"reasons": {}
},
{
"tool": "get_health",
"tags": [],
"reasons": {}
},
{
"tool": "setup_auth",
"tags": [],
"reasons": {}
},
{
"tool": "de_auth",
"tags": [],
"reasons": {}
},
{
"tool": "re_auth",
"tags": [],
"reasons": {}
},
{
"tool": "cleanup_data",
"tags": [],
"reasons": {}
},
{
"tool": "add_source",
"tags": [],
"reasons": {}
},
{
"tool": "generate_audio",
"tags": [],
"reasons": {}
},
{
"tool": "generate_content",
"tags": [],
"reasons": {}
},
{
"tool": "list_content",
"tags": [],
"reasons": {}
},
{
"tool": "download_audio",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
}
],
"surfaceDigest": "c0a6c61022ad611ecc71007cc38c5e3b1dd0381a3eac80b2b900b1875eb5f17b",
"stats": {
"tools": 26,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 3,
"low": 1,
"info": 0
}
}
}