Ibm Watsonx Data Intelligence — 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": "ibm-watsonx-data-intelligence-mcp-server",
"source": {
"kind": "package",
"origin": "ibm-watsonx-data-intelligence-mcp-server"
},
"server": {
"name": "ibm-watsonx-data-intelligence-mcp-server"
}
},
"grade": "A",
"score": {
"score": 96,
"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": "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": "moderate",
"reasons": [
"reads sensitive or local data"
],
"tags": [
"sensitive-source"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (2 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-006",
"title": "Reads a sensitive credential path or dumps the environment (app/shared/utils/tool_helper_service.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`app/shared/utils/tool_helper_service.py:697`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "app/shared/utils/tool_helper_service.py"
},
"evidence": "\\.pem|\\.key|\\.p12|\\.pfx|id_rsa|id_dsa|id_ed25519)[^\\s]*', '[FILE_PATH]', sanitized, flags=re.",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "app/shared/utils/tool_helper_service.py",
"line": 697,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (app/services/metadata_enrichment/tools/execute_term_generation.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`app/services/metadata_enrichment/tools/execute_term_generation.py:65`): 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": "app/services/metadata_enrichment/tools/execute_term_generation.py"
},
"evidence": "enrichment_common_utils import ( process_mdes_for_user_message ) mde_info, failed_mde_ids = await p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "app/services/metadata_enrichment/tools/execute_term_generation.py",
"line": 65,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (app/services/metadata_import/tools/create_metadata_import.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`app/services/metadata_import/tools/create_metadata_import.py:145`): 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": "app/services/metadata_import/tools/create_metadata_import.py"
},
"evidence": "\"Create a metadata import (MDI) in a project. Optionally specify a catalog to import metadata there instead of the",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "app/services/metadata_import/tools/create_metadata_import.py",
"line": 145,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (app/services/metadata_import/tools/pause_resume_or_cancel_mdi_job_run.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`app/services/metadata_import/tools/pause_resume_or_cancel_mdi_job_run.py:151`): 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": "app/services/metadata_import/tools/pause_resume_or_cancel_mdi_job_run.py"
},
"evidence": "e, or cancel a metadata import (MDI) job run. Use this single tool to control the lifecycle of an active metadata i",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "app/services/metadata_import/tools/pause_resume_or_cancel_mdi_job_run.py",
"line": 151,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (app/services/metadata_import/tools/search_metadata_import.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`app/services/metadata_import/tools/search_metadata_import.py:37`): 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": "app/services/metadata_import/tools/search_metadata_import.py"
},
"evidence": "want to use a metadata import (MDI). This function can search for all the available metadata imports (MDI) or searc",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "app/services/metadata_import/tools/search_metadata_import.py",
"line": 37,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"ibm-watsonx-data-intelligence-mcp-server\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "ibm-watsonx-data-intelligence-mcp-server"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "attach_url_contract_to_data_product",
"tags": [],
"reasons": {}
},
{
"tool": "my_tool",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "ff636b45d4de702273e4ac346c032df0e315f8b906c9a51bf788cae40350084e",
"stats": {
"tools": 2,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 4,
"low": 0,
"info": 1
}
}
}