Gdpr Shift Left — 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": "gdpr-shift-left-mcp",
"source": {
"kind": "package",
"origin": "gdpr-shift-left-mcp"
},
"server": {
"name": "gdpr-shift-left-mcp"
}
},
"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": [
"can send data / act on an external service"
],
"tags": [
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (34 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-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_enhanced_analyzers.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_enhanced_analyzers.py:238`): 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": "tests/test_enhanced_analyzers.py"
},
"evidence": "const response = await fetch('https://sheets.google.com/api/v4/spreadsheets'); return response.json();",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_enhanced_analyzers.py",
"line": 238,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (tests/evaluator/checks_adversarial.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/evaluator/checks_adversarial.py:2730`): 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/evaluator/checks_adversarial.py"
},
"evidence": "(\"eval_bypass\", \"new Function('return this.email')(); const password = 'x';\"), # Comment bypass attempts",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "tests/evaluator/checks_adversarial.py",
"line": 2730,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/evaluator/checks_adversarial.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/evaluator/checks_adversarial.py:2674`): 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/evaluator/checks_adversarial.py"
},
"evidence": "(\"exec_injection\", \"exec('import os; os.system(\\\"rm -rf /\\\")'); def get_email(): pass\"), (\"eval_injection\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/evaluator/checks_adversarial.py",
"line": 2674,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_bicep_templates.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_bicep_templates.py:34`): 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_bicep_templates.py"
},
"evidence": "try: result = subprocess.run( \"az bicep version\", capture_output=True, text=True, time",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_bicep_templates.py",
"line": 34,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "get_article",
"tags": [],
"reasons": {}
},
{
"tool": "list_chapter_articles",
"tags": [],
"reasons": {}
},
{
"tool": "search_gdpr",
"tags": [],
"reasons": {}
},
{
"tool": "get_recital",
"tags": [],
"reasons": {}
},
{
"tool": "get_azure_mapping",
"tags": [],
"reasons": {}
},
{
"tool": "get_definition",
"tags": [],
"reasons": {}
},
{
"tool": "list_definitions",
"tags": [],
"reasons": {}
},
{
"tool": "search_definitions",
"tags": [],
"reasons": {}
},
{
"tool": "assess_dpia_need",
"tags": [],
"reasons": {}
},
{
"tool": "generate_dpia_template",
"tags": [],
"reasons": {}
},
{
"tool": "get_dpia_guidance",
"tags": [],
"reasons": {}
},
{
"tool": "generate_ropa_template",
"tags": [],
"reasons": {}
},
{
"tool": "validate_ropa",
"tags": [],
"reasons": {}
},
{
"tool": "get_ropa_requirements",
"tags": [],
"reasons": {}
},
{
"tool": "get_dsr_guidance",
"tags": [],
"reasons": {}
},
{
"tool": "generate_dsr_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "get_dsr_timeline",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_infrastructure_code",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_application_code",
"tags": [],
"reasons": {}
},
{
"tool": "validate_gdpr_config",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_dsr_capabilities",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_cross_border_transfers",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_breach_readiness",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_data_flow",
"tags": [],
"reasons": {}
},
{
"tool": "assess_retention_policy",
"tags": [],
"reasons": {}
},
{
"tool": "get_retention_guidance",
"tags": [],
"reasons": {}
},
{
"tool": "check_deletion_requirements",
"tags": [],
"reasons": {}
},
{
"tool": "assess_controller_processor_role",
"tags": [],
"reasons": {}
},
{
"tool": "get_role_obligations",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_code_for_role_indicators",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
]
}
},
{
"tool": "generate_dpa_checklist",
"tags": [],
"reasons": {}
},
{
"tool": "get_role_scenarios",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_code_ast",
"tags": [],
"reasons": {}
},
{
"tool": "get_ast_capabilities",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "18cbd5a30cac984f34e7aa27c2b1188a2959c272bd75ee3d84bb081069cc7105",
"stats": {
"tools": 34,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 0,
"medium": 0,
"low": 4,
"info": 0
}
}
}