Sap Datasphere — 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": "sap-datasphere-mcp",
"source": {
"kind": "package",
"origin": "sap-datasphere-mcp"
},
"server": {
"name": "sap-datasphere-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)",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (49 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 (sap_datasphere_mcp_server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`sap_datasphere_mcp_server.py:3187`): 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": "sap_datasphere_mcp_server.py"
},
"evidence": "result = subprocess.run( [\"datasphere\", \"dbusers\", \"list\", \"--space\", space_id],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "sap_datasphere_mcp_server.py",
"line": 3187,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_no_live_tenant_data.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_no_live_tenant_data.py:158`): 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/test_no_live_tenant_data.py"
},
"evidence": "bprocess tracked = subprocess.run( [\"git\", \"ls-files\"], cwd=REPO, capture_output=True, text=True ).stdo",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_no_live_tenant_data.py",
"line": 158,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_sdk_v2_protocol.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_sdk_v2_protocol.py:214`): 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/test_sdk_v2_protocol.py"
},
"evidence": "ckname()[1] proc = subprocess.Popen( [sys.executable, \"-m\", \"sap_datasphere_mcp_server\", \"--transp",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_sdk_v2_protocol.py",
"line": 214,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "list_spaces",
"tags": [],
"reasons": {}
},
{
"tool": "get_space_info",
"tags": [],
"reasons": {}
},
{
"tool": "search_tables",
"tags": [],
"reasons": {}
},
{
"tool": "get_table_schema",
"tags": [],
"reasons": {}
},
{
"tool": "list_connections",
"tags": [],
"reasons": {}
},
{
"tool": "get_task_status",
"tags": [],
"reasons": {}
},
{
"tool": "browse_marketplace",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "find_assets_by_column",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_column_distribution",
"tags": [],
"reasons": {}
},
{
"tool": "execute_query",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"sql_query\"",
"parameter \"sql\""
]
}
},
{
"tool": "smart_query",
"tags": [],
"reasons": {}
},
{
"tool": "list_database_users",
"tags": [],
"reasons": {}
},
{
"tool": "create_database_user",
"tags": [],
"reasons": {}
},
{
"tool": "reset_database_user_password",
"tags": [],
"reasons": {}
},
{
"tool": "update_database_user",
"tags": [],
"reasons": {}
},
{
"tool": "delete_database_user",
"tags": [],
"reasons": {}
},
{
"tool": "list_catalog_assets",
"tags": [],
"reasons": {}
},
{
"tool": "get_asset_details",
"tags": [],
"reasons": {}
},
{
"tool": "get_asset_by_compound_key",
"tags": [],
"reasons": {}
},
{
"tool": "get_space_assets",
"tags": [],
"reasons": {}
},
{
"tool": "test_connection",
"tags": [],
"reasons": {}
},
{
"tool": "get_current_user",
"tags": [],
"reasons": {}
},
{
"tool": "get_tenant_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_available_scopes",
"tags": [],
"reasons": {}
},
{
"tool": "search_catalog",
"tags": [],
"reasons": {}
},
{
"tool": "search_repository",
"tags": [],
"reasons": {}
},
{
"tool": "get_catalog_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "get_consumption_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "get_analytical_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "get_relational_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "get_asset_variables",
"tags": [],
"reasons": {}
},
{
"tool": "list_relational_entities",
"tags": [],
"reasons": {}
},
{
"tool": "get_relational_entity_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "query_relational_entity",
"tags": [],
"reasons": {}
},
{
"tool": "get_relational_odata_service",
"tags": [],
"reasons": {}
},
{
"tool": "get_repository_search_metadata",
"tags": [],
"reasons": {}
},
{
"tool": "list_analytical_datasets",
"tags": [],
"reasons": {}
},
{
"tool": "get_analytical_model",
"tags": [],
"reasons": {}
},
{
"tool": "query_analytical_data",
"tags": [],
"reasons": {}
},
{
"tool": "get_analytical_service_document",
"tags": [],
"reasons": {}
},
{
"tool": "list_repository_objects",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "get_object_definition",
"tags": [],
"reasons": {}
},
{
"tool": "get_deployed_objects",
"tags": [],
"reasons": {}
},
{
"tool": "test_phase67_endpoints",
"tags": [],
"reasons": {}
},
{
"tool": "test_phase8_endpoints",
"tags": [],
"reasons": {}
},
{
"tool": "test_analytical_endpoints",
"tags": [],
"reasons": {}
},
{
"tool": "run_task_chain",
"tags": [],
"reasons": {}
},
{
"tool": "get_task_log",
"tags": [],
"reasons": {}
},
{
"tool": "get_task_history",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "a8b2faf39cbd15a6707d9d9960806eeee230ae285573ec58b743c7931a84c830",
"stats": {
"tools": 49,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 0,
"low": 2,
"info": 0
}
}
}