Turingmind — 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": "turingmind-mcp",
"source": {
"kind": "package",
"origin": "turingmind-mcp"
},
"server": {
"name": "turingmind-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": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"external-sink",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (99 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 (src/turingmind_mcp/auto_review_service.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/auto_review_service.py:119`): 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/turingmind_mcp/auto_review_service.py"
},
"evidence": "it result = subprocess.run( [\"git\", \"rev-parse\", \"--show-toplevel\"], capture",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/auto_review_service.py",
"line": 119,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/chat_capture.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/chat_capture.py:413`): 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/turingmind_mcp/chat_capture.py"
},
"evidence": "status result = subprocess.run( [\"git\", \"status\", \"--porcelain\", \"--untracked-files=all\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/chat_capture.py",
"line": 413,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/chat_observation_poller.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/chat_observation_poller.py:65`): 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/turingmind_mcp/chat_observation_poller.py"
},
"evidence": "try: url = subprocess.check_output( [\"git\", \"remote\", \"get-url\", \"origin\"], stderr=subprocess.D",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/chat_observation_poller.py",
"line": 65,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/client/client.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/client/client.py:59`): 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/turingmind_mcp/client/client.py"
},
"evidence": "self.process = subprocess.Popen( [self.command] + self.args, stdin=subprocess.P",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/client/client.py",
"line": 59,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/cursor_database_reader.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/cursor_database_reader.py:109`): 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/turingmind_mcp/cursor_database_reader.py"
},
"evidence": "query result = subprocess.run( cmd, input=sql, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/cursor_database_reader.py",
"line": 109,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/entity_indexer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/entity_indexer.py:455`): 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/turingmind_mcp/entity_indexer.py"
},
"evidence": "t root result = subprocess.run( [\"git\", \"rev-parse\", \"--show-toplevel\"], capture_output=",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/entity_indexer.py",
"line": 455,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/git_churn.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/git_churn.py:37`): 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/turingmind_mcp/git_churn.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"-C\", str(workspace), *args], capture_output=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/git_churn.py",
"line": 37,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/unified_cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/unified_cli.py:61`): 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/turingmind_mcp/unified_cli.py"
},
"evidence": "rocess subprocess.run([sys.executable, \"-m\", \"pip\", \"install\", \"turingmind-mcp\"]) print",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/unified_cli.py",
"line": 61,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/v2_engine/handlers.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/v2_engine/handlers.py:618`): 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/turingmind_mcp/v2_engine/handlers.py"
},
"evidence": "y: result = subprocess.run( [str(resolved_bin), \"-m\", \"pytest\", str(resolved_test_dir),",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/v2_engine/handlers.py",
"line": 618,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/turingmind_mcp/v2_engine/security_scanner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/turingmind_mcp/v2_engine/security_scanner.py:94`): 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/turingmind_mcp/v2_engine/security_scanner.py"
},
"evidence": "y: result = subprocess.run( [\"git\", \"diff\", \"--name-only\", \"--diff-filter=ACMR\", base_ref],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/turingmind_mcp/v2_engine/security_scanner.py",
"line": 94,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"webhook_url\" on \"turingmind_enable_auto_review\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"turingmind_enable_auto_review\" takes a URL/host parameter \"webhook_url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "turingmind_enable_auto_review",
"field": "inputSchema.properties.webhook_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "webhook_url"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "turingmind_initiate_login",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_poll_login",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_validate_auth",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_upload_review",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_context",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_submit_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_index_codebase",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_related_code",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_project_structure",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_edit_reasoning",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_list_memory",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_memory",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_save_memory",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_delete_memory",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_detect_conflicts",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_resolve_conflict",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_simulate_impact",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_explain_decision",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_memory_stats",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_enable_auto_review",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"parameter \"webhook\""
]
}
},
{
"tool": "turingmind_create_edit_plan",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_generate_spec",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_define_required_tests",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_validate_tests_written",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_request_code_edit",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_mark_test_written",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_validate_tests_passing",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_complete_tdd_cycle",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_tdd_status",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_audit_trail",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_kanban_data",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_analyze_diff",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_store_auto_plan",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_auto_plans",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_bundle_plans_for_commit",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_apply_edit",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_log_reasoning",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_store_chat_analysis_plan",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_chat_analysis_plans",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_decision",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_pending_decisions",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_resolve_decision",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_decision_stats",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_issue",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"create_issue\""
]
}
},
{
"tool": "turingmind_get_issue",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_list_issues",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_update_issue",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_is_issue_blocked",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_next_unblocked_issue",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_strategic_spec",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_strategic_spec",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_list_strategic_specs",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_update_strategic_spec",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_strategic_risk",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_strategic_risk",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_list_strategic_risks",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_update_strategic_risk",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_comment",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"create_comment\""
]
}
},
{
"tool": "turingmind_list_comments",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_goal",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_goal",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_list_goals",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_update_goal",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_initiative",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_initiative",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_list_initiatives",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_update_initiative",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_feature",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_feature",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_list_features",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_update_feature",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_break_down_feature",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_update_feature_progress",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_feature_issues",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_create_spec_node",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_update_spec_node",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_save_architecture_diagram",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_spec_status",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_list_spec_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_promote_node",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_ready_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_generate_verification",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_run_verification",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_record_execution_stage",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_classify_failure",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_apply_fix",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_apply_spec_delta",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_impacted_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_request_approval",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_execution_state",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_ingest_runtime_signal",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_bootstrap_codebase",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_get_decision_queue",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_sync_codebase",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_sync_cloud",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_test_opengrep_rule",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_register_rule",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_quarantine_rule",
"tags": [],
"reasons": {}
},
{
"tool": "turingmind_link_intent",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "5329eddaca164db6055796dc100380274c040bc5f13c10c7d2e9d67fdd0ab2e5",
"stats": {
"tools": 99,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 1,
"low": 0,
"info": 0
}
}
}