Google Automation — 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": "google-automation-mcp",
"source": {
"kind": "package",
"origin": "google-automation-mcp"
},
"server": {
"name": "google-automation-mcp"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"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 (60 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-CAP-001",
"title": "Tool \"run_script_function_tool\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_script_function_tool\" appears to run shell commands or evaluate code (keyword \"run_script\" in tool name). 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": "run_script_function_tool"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/google_automation_mcp/auth/clasp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/google_automation_mcp/auth/clasp.py:48`): 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": "src/google_automation_mcp/auth/clasp.py"
},
"evidence": "try: result = subprocess.run( [\"npx\", \"@google/clasp\", \"--version\"], capture_output=Tr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/google_automation_mcp/auth/clasp.py",
"line": 48,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/google_automation_mcp/router/script_template.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/google_automation_mcp/router/script_template.js:10`): 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/google_automation_mcp/router/script_template.js"
},
"evidence": "nt. try { UrlFetchApp.fetch('https://www.googleapis.com/tasks/v1/users/@me/lists?maxResults=1', { headers: {'Autho",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/google_automation_mcp/router/script_template.js",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_script_function_tool\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_script_function_tool\" 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": "run_script_function_tool"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"google-automation-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "google-automation-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "list_script_projects_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_script_project_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_script_content_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_script_project_tool",
"tags": [],
"reasons": {}
},
{
"tool": "delete_script_project_tool",
"tags": [],
"reasons": {}
},
{
"tool": "update_script_content_tool",
"tags": [],
"reasons": {}
},
{
"tool": "run_script_function_tool",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_script\" in tool name"
]
}
},
{
"tool": "create_deployment_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_deployments_tool",
"tags": [],
"reasons": {}
},
{
"tool": "update_deployment_tool",
"tags": [],
"reasons": {}
},
{
"tool": "delete_deployment_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_versions_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_version_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_version_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_script_processes_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_script_metrics_tool",
"tags": [],
"reasons": {}
},
{
"tool": "generate_trigger_code",
"tags": [],
"reasons": {}
},
{
"tool": "start_google_auth_tool",
"tags": [],
"reasons": {}
},
{
"tool": "complete_google_auth_tool",
"tags": [],
"reasons": {}
},
{
"tool": "search_gmail_messages_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_gmail_message_tool",
"tags": [],
"reasons": {}
},
{
"tool": "send_gmail_message_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_gmail_labels_tool",
"tags": [],
"reasons": {}
},
{
"tool": "modify_gmail_labels_tool",
"tags": [],
"reasons": {}
},
{
"tool": "search_drive_files_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_drive_items_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_drive_file_content_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_drive_file_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_drive_folder_tool",
"tags": [],
"reasons": {}
},
{
"tool": "delete_drive_file_tool",
"tags": [],
"reasons": {}
},
{
"tool": "trash_drive_file_tool",
"tags": [],
"reasons": {}
},
{
"tool": "share_drive_file_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_drive_permissions_tool",
"tags": [],
"reasons": {}
},
{
"tool": "remove_drive_permission_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_spreadsheets_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_sheet_values_tool",
"tags": [],
"reasons": {}
},
{
"tool": "update_sheet_values_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_spreadsheet_tool",
"tags": [],
"reasons": {}
},
{
"tool": "append_sheet_values_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_spreadsheet_metadata_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_calendars_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_events_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_event_tool",
"tags": [],
"reasons": {}
},
{
"tool": "delete_event_tool",
"tags": [],
"reasons": {}
},
{
"tool": "update_event_tool",
"tags": [],
"reasons": {}
},
{
"tool": "search_docs_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_doc_content_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_doc_tool",
"tags": [],
"reasons": {}
},
{
"tool": "modify_doc_text_tool",
"tags": [],
"reasons": {}
},
{
"tool": "append_doc_text_tool",
"tags": [],
"reasons": {}
},
{
"tool": "list_task_lists_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_tasks_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_task_tool",
"tags": [],
"reasons": {}
},
{
"tool": "update_task_tool",
"tags": [],
"reasons": {}
},
{
"tool": "delete_task_tool",
"tags": [],
"reasons": {}
},
{
"tool": "complete_task_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_form_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get_form_responses_tool",
"tags": [],
"reasons": {}
},
{
"tool": "create_form_tool",
"tags": [],
"reasons": {}
},
{
"tool": "add_form_question_tool",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "517c30a3a8bf38fa221c2df69323055050a03e6e99268c030fcb954ce38240cc",
"stats": {
"tools": 60,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 1,
"low": 1,
"info": 1
}
}
}