Pydoll — the complete, unedited output of the deterministic mcptrustchecker engine v1.8.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.8.0",
"methodologyVersion": "mcptrustchecker-1.8"
},
"target": {
"id": "pydoll-mcp",
"source": {
"kind": "package",
"origin": "pydoll-mcp"
},
"server": {
"name": "pydoll-mcp"
}
},
"grade": "B",
"score": {
"score": 89,
"threatScore": 100,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"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": "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-1.8"
},
"capability": {
"level": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"external-sink",
"sensitive-source",
"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 (57 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-FLOW-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: download_file → upload_file → execute_automation_script. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "download_file → upload_file → execute_automation_script"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"download_file",
"get_page_title",
"get_page_source",
"fetch_domain_commands"
],
"sources": [
"upload_file",
"download_file"
],
"sinks": [
"upload_file",
"export_to_csv",
"export_to_json",
"modify_request_headers",
"execute_javascript",
"execute_automation_script"
],
"path": [
"download_file",
"upload_file",
"execute_automation_script"
],
"edges": [
{
"from": "download_file",
"to": "upload_file",
"kind": "agent-mediated"
},
{
"from": "upload_file",
"to": "execute_automation_script",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-FLOW-003",
"title": "Read-and-egress in one tool: \"upload_file\"",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tool \"upload_file\" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.",
"remediation": "Separate reading from sending; require explicit user confirmation before egress of file/secret contents.",
"location": {
"kind": "flow",
"name": "upload_file"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"tags": [
"external-sink",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"execute_javascript\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"execute_javascript\" 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": "execute_javascript"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"execute_automation_script\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"execute_automation_script\" 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": "execute_automation_script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (publish.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`publish.py:41`): 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": "publish.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "publish.py",
"line": 41
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pydoll_mcp/__main__.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pydoll_mcp/__main__.py:30`): 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": "pydoll_mcp/__main__.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pydoll_mcp/__main__.py",
"line": 30
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pydoll_mcp/claude_setup.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pydoll_mcp/claude_setup.py:78`): 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": "pydoll_mcp/claude_setup.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pydoll_mcp/claude_setup.py",
"line": 78
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (pydoll_mcp/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`pydoll_mcp/server.py:151`): 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": "pydoll_mcp/server.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "pydoll_mcp/server.py",
"line": 151
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"download_file\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"download_file\" takes a URL/host parameter \"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_file",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"execute_javascript\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"execute_javascript\" 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": "execute_javascript",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script_name\" on \"execute_automation_script\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"execute_automation_script\" takes a command-shaped parameter \"script_name\" 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": "execute_automation_script",
"field": "inputSchema.properties.script_name"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script_name"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (pydoll_mcp/cli.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`pydoll_mcp/cli.py:90`): 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": "pydoll_mcp/cli.py"
},
"evidence": "__import__(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "pydoll_mcp/cli.py",
"line": 90
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"execute_javascript\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"execute_javascript\" 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": "execute_javascript"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"execute_automation_script\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"execute_automation_script\" 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": "execute_automation_script"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"file_path\" on \"upload_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"upload_file\" takes a path parameter \"file_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "upload_file",
"field": "inputSchema.properties.file_path"
},
"data": {
"param": "file_path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"save_path\" on \"download_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"download_file\" takes a path parameter \"save_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "download_file",
"field": "inputSchema.properties.save_path"
},
"data": {
"param": "save_path"
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/conftest.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/conftest.py:312`): 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": "tests/conftest.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/conftest.py",
"line": 312
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"download_file",
"get_page_title",
"get_page_source",
"fetch_domain_commands"
],
"sensitiveSource": [
"upload_file",
"download_file"
],
"externalSink": [
"upload_file",
"export_to_csv",
"export_to_json",
"modify_request_headers",
"execute_javascript",
"execute_automation_script"
],
"selfContained": false,
"path": [
"download_file",
"upload_file",
"execute_automation_script"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: download_file → upload_file → execute_automation_script."
},
{
"id": "flow-2",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"upload_file"
],
"externalSink": [
"upload_file"
],
"selfContained": true,
"description": "Tool \"upload_file\" both reads sensitive data and can send it externally."
}
],
"capabilities": [
{
"tool": "analyze_performance",
"tags": [],
"reasons": {}
},
{
"tool": "intercept_network_requests",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_content_with_ai",
"tags": [],
"reasons": {}
},
{
"tool": "start_browser",
"tags": [],
"reasons": {}
},
{
"tool": "stop_browser",
"tags": [],
"reasons": {}
},
{
"tool": "list_browsers",
"tags": [],
"reasons": {}
},
{
"tool": "get_browser_status",
"tags": [],
"reasons": {}
},
{
"tool": "new_tab",
"tags": [],
"reasons": {}
},
{
"tool": "close_tab",
"tags": [],
"reasons": {}
},
{
"tool": "list_tabs",
"tags": [],
"reasons": {}
},
{
"tool": "set_active_tab",
"tags": [],
"reasons": {}
},
{
"tool": "find_element",
"tags": [],
"reasons": {}
},
{
"tool": "click_element",
"tags": [],
"reasons": {}
},
{
"tool": "type_text",
"tags": [],
"reasons": {}
},
{
"tool": "get_parent_element",
"tags": [],
"reasons": {}
},
{
"tool": "upload_file",
"tags": [
"external-sink",
"sensitive-source"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
],
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "download_file",
"tags": [
"untrusted-input",
"sensitive-source"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
],
"sensitive-source": [
"parameter \"path\""
]
}
},
{
"tool": "manage_downloads",
"tags": [],
"reasons": {}
},
{
"tool": "extract_data",
"tags": [],
"reasons": {}
},
{
"tool": "export_to_csv",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"export_to\""
]
}
},
{
"tool": "export_to_json",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"export_to\""
]
}
},
{
"tool": "save_session",
"tags": [],
"reasons": {}
},
{
"tool": "load_session",
"tags": [],
"reasons": {}
},
{
"tool": "navigate_to",
"tags": [],
"reasons": {}
},
{
"tool": "refresh_page",
"tags": [],
"reasons": {}
},
{
"tool": "go_back",
"tags": [],
"reasons": {}
},
{
"tool": "get_current_url",
"tags": [],
"reasons": {}
},
{
"tool": "get_page_title",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "get_page_source",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "fetch_domain_commands",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "get_network_logs",
"tags": [],
"reasons": {}
},
{
"tool": "block_requests",
"tags": [],
"reasons": {}
},
{
"tool": "modify_request_headers",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"http_request\""
]
}
},
{
"tool": "extract_api_responses",
"tags": [],
"reasons": {}
},
{
"tool": "monitor_websockets",
"tags": [],
"reasons": {}
},
{
"tool": "throttle_network",
"tags": [],
"reasons": {}
},
{
"tool": "clear_cache",
"tags": [],
"reasons": {}
},
{
"tool": "save_har",
"tags": [],
"reasons": {}
},
{
"tool": "enable_stealth_mode",
"tags": [],
"reasons": {}
},
{
"tool": "bypass_cloudflare",
"tags": [],
"reasons": {}
},
{
"tool": "bypass_recaptcha",
"tags": [],
"reasons": {}
},
{
"tool": "simulate_human_behavior",
"tags": [],
"reasons": {}
},
{
"tool": "randomize_fingerprint",
"tags": [],
"reasons": {}
},
{
"tool": "set_user_agent",
"tags": [],
"reasons": {}
},
{
"tool": "handle_bot_detection",
"tags": [],
"reasons": {}
},
{
"tool": "evade_detection",
"tags": [],
"reasons": {}
},
{
"tool": "rotate_proxy",
"tags": [],
"reasons": {}
},
{
"tool": "check_protection_status",
"tags": [],
"reasons": {}
},
{
"tool": "spoof_headers",
"tags": [],
"reasons": {}
},
{
"tool": "randomize_timing",
"tags": [],
"reasons": {}
},
{
"tool": "take_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "take_element_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "generate_pdf",
"tags": [],
"reasons": {}
},
{
"tool": "execute_javascript",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "execute_automation_script",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "inject_script_library",
"tags": [],
"reasons": {}
},
{
"tool": "intelligent_search",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "8aeda6abfc3b06dabdbec4f266027ff9f47dc7515e904bfe44989fd7b8de4721",
"stats": {
"tools": 57,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 7,
"medium": 4,
"low": 5,
"info": 0
}
}
}