Lasso — 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": "lasso-mcp",
"source": {
"kind": "package",
"origin": "lasso-mcp"
},
"server": {
"name": "lasso-mcp"
}
},
"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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (19 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/desktop/desktop-doctor-checks.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/desktop/desktop-doctor-checks.js:27`): 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/desktop/desktop-doctor-checks.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import { existsSync } from \"node:fs\"; //",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/desktop/desktop-doctor-checks.js",
"line": 27,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/doctor/doctor.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/doctor/doctor.js:93`): 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/doctor/doctor.js"
},
"evidence": "ecFileSync } from \"node:child_process\"; import { promisify } from \"node:util\"; import { promises as fs, constants as fsC",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/doctor/doctor.js",
"line": 93,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/launcher/chrome-hide.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/launcher/chrome-hide.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": "dist/launcher/chrome-hide.js"
},
"evidence": ", execFile } from \"node:child_process\"; import process from \"node:process\"; /** * 按 unix id 定向 hide 一个 Chrome 进程（AppleS",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/launcher/chrome-hide.js",
"line": 19,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/launcher/chrome-hideshow-cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/launcher/chrome-hideshow-cli.js:28`): 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/launcher/chrome-hideshow-cli.js"
},
"evidence": "spawnSync } from \"node:child_process\"; import process from \"node:process\"; import * as path from \"node:path\"; import os",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/launcher/chrome-hideshow-cli.js",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/launcher/chrome-stop.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/launcher/chrome-stop.js:28`): 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/launcher/chrome-stop.js"
},
"evidence": "spawnSync } from \"node:child_process\"; import { rmSync } from \"node:fs\"; import * as path from \"node:path\"; import proc",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/launcher/chrome-stop.js",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/launcher/desired-hide-enforcer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/launcher/desired-hide-enforcer.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/launcher/desired-hide-enforcer.js"
},
"evidence": "spawnSync } from \"node:child_process\"; import { accessSync, readFileSync, writeFileSync, mkdirSync } from \"node:fs\"; im",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/launcher/desired-hide-enforcer.js",
"line": 26,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/launcher/desired-hide-watchdog.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/launcher/desired-hide-watchdog.js:25`): 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/launcher/desired-hide-watchdog.js"
},
"evidence": "spawnSync } from \"node:child_process\"; import { readDesiredHiddenSync, rewriteDesiredHiddenSync, } from \"./desired-hide",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/launcher/desired-hide-watchdog.js",
"line": 25,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/launcher/launch-chrome.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/launcher/launch-chrome.js:35`): 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/launcher/launch-chrome.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { promises as fs, constants as fsConstants } from \"node:fs\"; import * as",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/launcher/launch-chrome.js",
"line": 35,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/logged-in/keychain.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/logged-in/keychain.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/logged-in/keychain.js"
},
"evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import { randomBytes } from \"node:crypto\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/logged-in/keychain.js",
"line": 18,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/render/render-doctor.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/render/render-doctor.js:37`): 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/render/render-doctor.js"
},
"evidence": "spawnSync } from \"node:child_process\"; import { readdirSync, rmSync, statSync } from \"node:fs\"; import * as path from \"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/render/render-doctor.js",
"line": 37,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/channels/BrowserbaseChannel.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/channels/BrowserbaseChannel.js:49`): 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": "dist/channels/BrowserbaseChannel.js"
},
"evidence": "> { const r = await fetch(\"https://api.browserbase.com/v1/sessions\", { method: \"POST\", headers: {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/channels/BrowserbaseChannel.js",
"line": 49,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/doctor/doctor.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/doctor/doctor.js:2398`): 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": "dist/doctor/doctor.js"
},
"evidence": "const resp = await fetch(\"https://api.stagehand.dev/verify\", { method: \"HEAD\", signal: Abor",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/doctor/doctor.js",
"line": 2398,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/channels/BrowserbaseChannel.ts)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/channels/BrowserbaseChannel.ts:74`): 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": "src/channels/BrowserbaseChannel.ts"
},
"evidence": "=> { const r = await fetch(\"https://api.browserbase.com/v1/sessions\", { method: \"POST\", headers: { Auth",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/channels/BrowserbaseChannel.ts",
"line": 74,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/doctor/doctor.ts)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/doctor/doctor.ts:3017`): 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": "src/doctor/doctor.ts"
},
"evidence": "const resp = await fetch(\"https://api.stagehand.dev/verify\", { method: \"HEAD\", signal: AbortSignal.time",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/doctor/doctor.ts",
"line": 3017,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "search_local",
"tags": [],
"reasons": {}
},
{
"tool": "browse_headless",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "browse_logged_in",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "browserbase",
"tags": [],
"reasons": {}
},
{
"tool": "desktop",
"tags": [],
"reasons": {}
},
{
"tool": "doctor",
"tags": [],
"reasons": {}
},
{
"tool": "fetch_feed",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "fetch_url",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch_url\""
]
}
},
{
"tool": "interact_roots",
"tags": [],
"reasons": {}
},
{
"tool": "interact_observe",
"tags": [],
"reasons": {}
},
{
"tool": "interact_act",
"tags": [],
"reasons": {}
},
{
"tool": "network",
"tags": [],
"reasons": {}
},
{
"tool": "pdf",
"tags": [],
"reasons": {}
},
{
"tool": "read_text",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "search",
"tags": [],
"reasons": {}
},
{
"tool": "steel",
"tags": [],
"reasons": {}
},
{
"tool": "wayback_lookup",
"tags": [],
"reasons": {}
},
{
"tool": "markdown...",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d27575cb82db4817d0c2d1417e58f695f0a1de8e19519ed1d85cdb353d20d4a5",
"stats": {
"tools": 19,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 4,
"low": 0,
"info": 0
}
}
}