Box — 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": "mcp-server-box",
"source": {
"kind": "package",
"origin": "mcp-server-box"
},
"server": {
"name": "mcp-server-box"
}
},
"grade": "A",
"score": {
"score": 95,
"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": "moderate",
"label": "capability blast radius (moderate) — client exposure if the model is manipulated",
"appliedPenalty": 3
},
{
"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": "moderate",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service"
],
"tags": [
"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 (30 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-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([box_ask_ai_tool, box_hubs_ask_ai_tool, box_download_file_tool, box_docgen_get_job_tool]) co-exist with external-action tools ([box_upload_file_from_path_tool, box_upload_file_from_content_tool, box_chunked_upload_file_tool]). 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": "box_ask_ai_tool → box_upload_file_from_path_tool"
},
"evidence": "untrusted [box_ask_ai_tool, box_hubs_ask_ai_tool, box_download_file_tool, box_docgen_get_job_tool] → sinks [box_upload_file_from_path_tool, box_upload_file_from",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"box_ask_ai_tool",
"box_hubs_ask_ai_tool",
"box_download_file_tool",
"box_docgen_get_job_tool"
],
"sinks": [
"box_upload_file_from_path_tool",
"box_upload_file_from_content_tool",
"box_chunked_upload_file_tool"
]
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/test_box_api_ai.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_box_api_ai.py:29`): 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": "tests/test_box_api_ai.py"
},
"evidence": "tr to dict answer = eval(answer) assert isinstance(answer, dict) assert answer.get(\"contract date\") is not N",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/test_box_api_ai.py",
"line": 29,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"mcp-server-box\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "mcp-server-box"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"mcp-server-box\" 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": "mcp-server-box"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"box_ask_ai_tool",
"box_hubs_ask_ai_tool",
"box_download_file_tool",
"box_docgen_get_job_tool"
],
"sensitiveSource": [],
"externalSink": [
"box_upload_file_from_path_tool",
"box_upload_file_from_content_tool",
"box_chunked_upload_file_tool"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "box_who_am_i",
"tags": [],
"reasons": {}
},
{
"tool": "box_authorize_app_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_search_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_read_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_ask_ai_tool",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_pr\""
]
}
},
{
"tool": "box_ask_ai_tool_multi_file",
"tags": [],
"reasons": {}
},
{
"tool": "box_hubs_ask_ai_tool",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"read_pr\""
]
}
},
{
"tool": "box_search_folder_by_name",
"tags": [],
"reasons": {}
},
{
"tool": "box_ai_extract_data",
"tags": [],
"reasons": {}
},
{
"tool": "box_list_folder_content_by_folder_id",
"tags": [],
"reasons": {}
},
{
"tool": "box_manage_folder_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_upload_file_from_path_tool",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "box_upload_file_from_content_tool",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "box_download_file_tool",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "box_docgen_create_batch_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_docgen_get_job_tool",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "box_docgen_list_jobs_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_docgen_list_jobs_by_batch_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_docgen_template_create_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_docgen_template_list_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_docgen_template_delete_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_docgen_template_get_by_id_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_docgen_template_list_tags_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_docgen_template_list_jobs_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_create_share_link_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_get_shared_link_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_remove_shared_link_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_upload_folder_recursive_tool",
"tags": [],
"reasons": {}
},
{
"tool": "box_chunked_upload_file_tool",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "box_chunked_upload_new_version_tool",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d8a8e807a0928e1efe7a6dec69c1636934fdcb976fe03de2c7a499822c642e4b",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 1,
"low": 1,
"info": 2
}
}
}