Raw scan report

Browser Use — 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.

← Back to the scan page
{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.13.0",
    "methodologyVersion": "mcptrustchecker-1.13"
  },
  "target": {
    "id": "browser-use",
    "source": {
      "kind": "package",
      "origin": "browser-use"
    },
    "server": {
      "name": "browser-use"
    }
  },
  "grade": "A",
  "score": {
    "score": 93,
    "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": "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": "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": [
      "code-exec",
      "untrusted-input",
      "external-sink"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (27 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/dom/service.js)",
      "category": "injection",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/dom/service.js:97`): 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/dom/service.js"
      },
      "evidence": "const fn = eval(script); return fn(evaluateArgs); }, { script: this.jsCode, eva",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-010",
        "file": "dist/dom/service.js",
        "line": 97,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"browser_exec\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"browser_exec\" appears to run shell commands or evaluate code (keyword \"exec\" in tool name, parameter \"command\"). 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": "browser_exec"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (dist/dom/service.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/dom/service.js:97`): 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/dom/service.js"
      },
      "evidence": "const fn = eval(script); return fn(evaluateArgs); }, { script: this.jsCode, eva",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "dist/dom/service.js",
        "line": 97,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/browser/session.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/browser/session.js:6`): 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/browser/session.js"
      },
      "evidence": "cFileSync, } from 'node:child_process'; import { promisify } from 'node:util'; import { createLogger } from '../logging-",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/browser/session.js",
        "line": 6,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/cli.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/cli.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": "dist/cli.js"
      },
      "evidence": "spawnSync } from 'node:child_process'; import { createRequire } from 'node:module'; import { stdin, stdout } from 'node",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/cli.js",
        "line": 4,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/filesystem/file-system.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/filesystem/file-system.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/filesystem/file-system.js"
      },
      "evidence": "spawnSync } from 'node:child_process'; const require = createRequire(import.meta.url); const chmodPrivatePath = (target",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/filesystem/file-system.js",
        "line": 10,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/process-identity.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/process-identity.js:2`): 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/process-identity.js"
      },
      "evidence": "spawnSync } from 'node:child_process'; export const PROCESS_INSPECTION_TIMEOUT_MS = 5_000; export const MAX_PROCESS_INS",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/process-identity.js",
        "line": 2,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/skill-cli/direct.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/skill-cli/direct.js:6`): 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/skill-cli/direct.js"
      },
      "evidence": "spawnSync } from 'node:child_process'; import { chromium } from 'playwright'; import { BrowserSession, systemChrome } f",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/skill-cli/direct.js",
        "line": 6,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/skill-cli/tunnel.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/skill-cli/tunnel.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": "dist/skill-cli/tunnel.js"
      },
      "evidence": "spawnSync } from 'node:child_process'; import { randomUUID } from 'node:crypto'; import { getProcessArguments, } from '",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/skill-cli/tunnel.js",
        "line": 4,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/utils.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/utils.js:1`): 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/utils.js"
      },
      "evidence": "{ execSync } from 'node:child_process'; import crypto from 'node:crypto'; import fs from 'node:fs'; import os from 'node",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/utils.js",
        "line": 1,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-FLOW-005",
      "title": "Untrusted input can drive an external action",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "Untrusted-input tools ([scrape_data, url]) co-exist with external-action tools ([browser_exec]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
      "remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
      "location": {
        "kind": "flow",
        "name": "scrape_data → browser_exec"
      },
      "evidence": "untrusted [scrape_data, url] → sinks [browser_exec]",
      "owasp": "LLM06:2025 Excessive Agency",
      "references": [],
      "data": {
        "untrusted": [
          "scrape_data",
          "url"
        ],
        "sinks": [
          "browser_exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (dist/utils.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/utils.js:255`): 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/utils.js"
      },
      "evidence": "const response = await fetch('https://registry.npmjs.org/browser-use/latest', { method: 'GET',",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "dist/utils.js",
        "line": 255,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-006",
      "title": "Unconstrained command parameter \"command\" on \"browser_exec\"",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"browser_exec\" takes a command-shaped parameter \"command\" 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": "browser_exec",
        "field": "inputSchema.properties.command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "param": "command"
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"browser_exec\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"browser_exec\" 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": "browser_exec"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SUP-010",
      "title": "Package runs install-time scripts (postinstall)",
      "category": "supply-chain",
      "severity": "low",
      "confidence": "heuristic",
      "description": "\"browser-use\" 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": "browser-use"
      },
      "evidence": "playwright install chromium",
      "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": [
    {
      "id": "flow-1",
      "severity": "medium",
      "confidence": "strong",
      "untrustedInput": [
        "scrape_data",
        "url"
      ],
      "sensitiveSource": [],
      "externalSink": [
        "browser_exec"
      ],
      "selfContained": false,
      "description": "Untrusted input can drive an external action even though no sensitive source is exposed."
    }
  ],
  "capabilities": [
    {
      "tool": "browser_exec",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"exec\" in tool name",
          "parameter \"command\""
        ]
      }
    },
    {
      "tool": "browser_screenshot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_navigate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_click",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_type",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_get_state",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_extract_content",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_scroll",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_go_back",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_list_tabs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_switch_tab",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_close_tab",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_list_sessions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_close_session",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "browser_close_all",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "retry_with_browser_use_agent",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "scrape_data",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "url",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"scrape\""
        ]
      }
    },
    {
      "tool": "data_type",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "fill_form",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "field_data",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "multi_step_task",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "task_description",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "max_steps",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "research_topic",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "topic",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sites",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "a87bc2c9aece97acd759455cd72a5b6ef3cc32a9ea03219dacc032d590eefee7",
  "stats": {
    "tools": 27,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 10,
      "medium": 3,
      "low": 2,
      "info": 0
    }
  }
}