Elite Reasoning — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "elite-reasoning-mcp",
"source": {
"kind": "package",
"origin": "elite-reasoning-mcp"
},
"server": {
"name": "elite-reasoning-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-1.9"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (92 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-CAP-001",
"title": "Tool \"run_elite_eval_suite\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_elite_eval_suite\" appears to run shell commands or evaluate code (keyword \"eval\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "run_elite_eval_suite"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"export_eval_harness\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"export_eval_harness\" appears to run shell commands or evaluate code (keyword \"eval\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "export_eval_harness"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (test_quality_gate.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`test_quality_gate.py:22`): 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": "test_quality_gate.py"
},
"evidence": "ubprocess process = subprocess.Popen( [sys.executable, \"-m\", \"uvicorn\", \"core.integration.sync_server:app\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "test_quality_gate.py",
"line": 22,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (test_team_sync.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`test_team_sync.py:23`): 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": "test_team_sync.py"
},
"evidence": "nd server_process = subprocess.Popen( [sys.executable, \"core/integration/sync_server.py\"], stdout=su",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "test_team_sync.py",
"line": 23,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([validate_predictions, browse_tool_usage, introspect]) co-exist with external-action tools ([run_elite_eval_suite, export_eval_harness]). 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": "validate_predictions → run_elite_eval_suite"
},
"evidence": "untrusted [validate_predictions, browse_tool_usage, introspect] → sinks [run_elite_eval_suite, export_eval_harness]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"validate_predictions",
"browse_tool_usage",
"introspect"
],
"sinks": [
"run_elite_eval_suite",
"export_eval_harness"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_elite_eval_suite\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_elite_eval_suite\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "run_elite_eval_suite"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"export_eval_harness\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"export_eval_harness\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "export_eval_harness"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/release_check.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/release_check.py:27`): 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": "scripts/release_check.py"
},
"evidence": "> {name}\") result = subprocess.run(command, cwd=ROOT) if result.returncode != 0: raise SystemExit(result",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/release_check.py",
"line": 27,
"nonRuntime": true
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"validate_predictions",
"browse_tool_usage",
"introspect"
],
"sensitiveSource": [],
"externalSink": [
"run_elite_eval_suite",
"export_eval_harness"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "get_user_profile",
"tags": [],
"reasons": {}
},
{
"tool": "update_user_config",
"tags": [],
"reasons": {}
},
{
"tool": "list_team_users",
"tags": [],
"reasons": {}
},
{
"tool": "share_skill",
"tags": [],
"reasons": {}
},
{
"tool": "memory_sync_decisions",
"tags": [],
"reasons": {}
},
{
"tool": "memory_sync_mistakes",
"tags": [],
"reasons": {}
},
{
"tool": "memory_sync_rules",
"tags": [],
"reasons": {}
},
{
"tool": "memory_search_context",
"tags": [],
"reasons": {}
},
{
"tool": "record_prompt_intent",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_prompt_sequence",
"tags": [],
"reasons": {}
},
{
"tool": "get_user_thinking_model",
"tags": [],
"reasons": {}
},
{
"tool": "update_thinking_pattern",
"tags": [],
"reasons": {}
},
{
"tool": "autonomous_scan",
"tags": [],
"reasons": {}
},
{
"tool": "register_prevention_rule",
"tags": [],
"reasons": {}
},
{
"tool": "self_diagnose",
"tags": [],
"reasons": {}
},
{
"tool": "generate_autonomous_goals",
"tags": [],
"reasons": {}
},
{
"tool": "get_autonomous_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_tool_usage_stats",
"tags": [],
"reasons": {}
},
{
"tool": "list_prevention_rules",
"tags": [],
"reasons": {}
},
{
"tool": "delete_prevention_rule",
"tags": [],
"reasons": {}
},
{
"tool": "predictive_prevention",
"tags": [],
"reasons": {}
},
{
"tool": "five_whys",
"tags": [],
"reasons": {}
},
{
"tool": "fmea_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "after_action_review",
"tags": [],
"reasons": {}
},
{
"tool": "smoke_test_gate",
"tags": [],
"reasons": {}
},
{
"tool": "simulate_future_regrets",
"tags": [],
"reasons": {}
},
{
"tool": "fmea_risk_gate",
"tags": [],
"reasons": {}
},
{
"tool": "calculate_expected_value",
"tags": [],
"reasons": {}
},
{
"tool": "bayesian_update",
"tags": [],
"reasons": {}
},
{
"tool": "compound_growth",
"tags": [],
"reasons": {}
},
{
"tool": "record_mistake",
"tags": [],
"reasons": {}
},
{
"tool": "record_decision",
"tags": [],
"reasons": {}
},
{
"tool": "search_decisions",
"tags": [],
"reasons": {}
},
{
"tool": "record_quality_score",
"tags": [],
"reasons": {}
},
{
"tool": "get_quality_trend",
"tags": [],
"reasons": {}
},
{
"tool": "pre_commit_audit",
"tags": [],
"reasons": {}
},
{
"tool": "swiss_cheese_audit",
"tags": [],
"reasons": {}
},
{
"tool": "bias_scan",
"tags": [],
"reasons": {}
},
{
"tool": "benchmark_track",
"tags": [],
"reasons": {}
},
{
"tool": "record_prospective_failure",
"tags": [],
"reasons": {}
},
{
"tool": "validate_predictions",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "elite_doctor",
"tags": [],
"reasons": {}
},
{
"tool": "elite_doctor_json",
"tags": [],
"reasons": {}
},
{
"tool": "polish_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "get_prompt_quality_trend",
"tags": [],
"reasons": {}
},
{
"tool": "record_hypothesis",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_hypothesis",
"tags": [],
"reasons": {}
},
{
"tool": "ingest_context",
"tags": [],
"reasons": {}
},
{
"tool": "query_temporal_graph",
"tags": [],
"reasons": {}
},
{
"tool": "orchestrate_request_tool",
"tags": [],
"reasons": {}
},
{
"tool": "verify_capabilities_tool",
"tags": [],
"reasons": {}
},
{
"tool": "research_benchmark_catalog",
"tags": [],
"reasons": {}
},
{
"tool": "elite_outcome_scorecard",
"tags": [],
"reasons": {}
},
{
"tool": "roi_tool_budget",
"tags": [],
"reasons": {}
},
{
"tool": "nuclear_prompt_breakdown",
"tags": [],
"reasons": {}
},
{
"tool": "select_reasoning_protocol",
"tags": [],
"reasons": {}
},
{
"tool": "build_experiment_tree",
"tags": [],
"reasons": {}
},
{
"tool": "run_elite_eval_suite",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "recommend_open_source_integrations",
"tags": [],
"reasons": {}
},
{
"tool": "export_eval_harness",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "get_elite_workflow",
"tags": [],
"reasons": {}
},
{
"tool": "check_anti_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "adopt_vs_build",
"tags": [],
"reasons": {}
},
{
"tool": "set_goal",
"tags": [],
"reasons": {}
},
{
"tool": "check_goals",
"tags": [],
"reasons": {}
},
{
"tool": "update_goal",
"tags": [],
"reasons": {}
},
{
"tool": "archive_goal",
"tags": [],
"reasons": {}
},
{
"tool": "delete_goal",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_prospective_failure",
"tags": [],
"reasons": {}
},
{
"tool": "sync_team_memory",
"tags": [],
"reasons": {}
},
{
"tool": "assess_confidence",
"tags": [],
"reasons": {}
},
{
"tool": "socratic_challenge",
"tags": [],
"reasons": {}
},
{
"tool": "reasoning_preflight",
"tags": [],
"reasons": {}
},
{
"tool": "calibration_predict",
"tags": [],
"reasons": {}
},
{
"tool": "calibration_resolve",
"tags": [],
"reasons": {}
},
{
"tool": "calibration_score",
"tags": [],
"reasons": {}
},
{
"tool": "decision_council_review",
"tags": [],
"reasons": {}
},
{
"tool": "record_missed_detection",
"tags": [],
"reasons": {}
},
{
"tool": "browse_tool_usage",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "search_thinking_patterns",
"tags": [],
"reasons": {}
},
{
"tool": "plan",
"tags": [],
"reasons": {}
},
{
"tool": "audit",
"tags": [],
"reasons": {}
},
{
"tool": "analyze",
"tags": [],
"reasons": {}
},
{
"tool": "remember",
"tags": [],
"reasons": {}
},
{
"tool": "predict",
"tags": [],
"reasons": {}
},
{
"tool": "learn",
"tags": [],
"reasons": {}
},
{
"tool": "introspect",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "workflow_run",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_status",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_update_step",
"tags": [],
"reasons": {}
},
{
"tool": "remember_context",
"tags": [],
"reasons": {}
},
{
"tool": "memory_context_pack",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "0b5b270f270b84f8a3237049e6ddbe831c78d2932a7cdaca357e0e0822773576",
"stats": {
"tools": 92,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 1,
"low": 3,
"info": 0
}
}
}