Cortex — 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": "cortex-mcp",
"source": {
"kind": "package",
"origin": "cortex-mcp"
},
"server": {
"name": "cortex-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 create, modify or delete files",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"file-write",
"sensitive-source",
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (53 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 (cortex_mcp/hooks/validate_boundary.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/hooks/validate_boundary.py:29`): 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": "cortex_mcp/hooks/validate_boundary.py"
},
"evidence": "r\"\\.gitconfig\", r\"id_rsa\", r\"id_ed25519\", r\"\\.npmrc\", r\"\\.pypirc\", ] # 위험 명령어 패턴 DANGEROUS_COMMANDS =",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "cortex_mcp/hooks/validate_boundary.py",
"line": 29,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/auto_verifier.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/auto_verifier.py:758`): 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": "cortex_mcp/core/auto_verifier.py"
},
"evidence": "\"] result = subprocess.run( git_diff_cmd, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/auto_verifier.py",
"line": 758,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/claim_verifier.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/claim_verifier.py:681`): 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": "cortex_mcp/core/claim_verifier.py"
},
"evidence": "result = subprocess.run( cmd, cwd=self.project_path,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/claim_verifier.py",
"line": 681,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/evidence_collector.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/evidence_collector.py:273`): 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": "cortex_mcp/core/evidence_collector.py"
},
"evidence": "y: result = subprocess.run( [\"git\"] + args, cwd=self.project_path,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/evidence_collector.py",
"line": 273,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/git_sync.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/git_sync.py:91`): 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": "cortex_mcp/core/git_sync.py"
},
"evidence": "오기 result = subprocess.run( [\"git\", \"rev-parse\", \"--abbrev-ref\", \"HEAD\"], cw",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/git_sync.py",
"line": 91,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/license_manager.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/license_manager.py:358`): 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": "cortex_mcp/core/license_manager.py"
},
"evidence": "result = subprocess.run( [\"sysctl\", \"-n\", \"machdep.cpu.brand_string\"], capture_output",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/license_manager.py",
"line": 358,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/memory/context_loader.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/memory/context_loader.py:279`): 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": "cortex_mcp/core/memory/context_loader.py"
},
"evidence": "result = subprocess.run( [\"git\", \"branch\", \"--show-current\"], cwd",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/memory/context_loader.py",
"line": 279,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/memory_manager.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/memory_manager.py:833`): 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": "cortex_mcp/core/memory_manager.py"
},
"evidence": "try: subprocess.run( [\"git\", \"--version\"], check=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/memory_manager.py",
"line": 833,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/project_config.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/project_config.py:157`): 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": "cortex_mcp/core/project_config.py"
},
"evidence": "오기 result = subprocess.run( [\"git\", \"remote\", \"get-url\", \"origin\"], cwd=self",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/project_config.py",
"line": 157,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/team_merge.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/team_merge.py:117`): 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": "cortex_mcp/core/team_merge.py"
},
"evidence": "확인 result = subprocess.run( [\"git\", \"log\", \"-1\", \"--pretty=%P\"], cwd=repo_pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/team_merge.py",
"line": 117,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (cortex_mcp/core/verifiers/file_change_verifier.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/core/verifiers/file_change_verifier.py:263`): 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": "cortex_mcp/core/verifiers/file_change_verifier.py"
},
"evidence": "e] result = subprocess.run( cmd, cwd=project_path, capture_o",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "cortex_mcp/core/verifiers/file_change_verifier.py",
"line": 263,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (cortex_mcp/cli.py)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`cortex_mcp/cli.py:63`): 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": "cortex_mcp/cli.py"
},
"evidence": "try: response = requests.get( \"https://pypi.org/pypi/cortex-mcp/json\", timeout=5",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "cortex_mcp/cli.py",
"line": 63,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"unlink_git_branch\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"unlink_git_branch\" can write, overwrite or delete files (keyword \"unlink\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "unlink_git_branch"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (cortex_mcp/cli.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`cortex_mcp/cli.py:154`): 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": "cortex_mcp/cli.py"
},
"evidence": "try: __import__(module) print(f\" [PASS] {name}\") except ImportError:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "cortex_mcp/cli.py",
"line": 154,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"unlink_git_branch\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"unlink_git_branch\" 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": "unlink_git_branch"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"repo_path\" on \"unlink_git_branch\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"unlink_git_branch\" takes a path parameter \"repo_path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "unlink_git_branch",
"field": "inputSchema.properties.repo_path"
},
"data": {
"param": "repo_path"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal in packaging/dev tooling (cortex_mcp/scripts/verify_installation.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`cortex_mcp/scripts/verify_installation.py:133`): 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": "cortex_mcp/scripts/verify_installation.py"
},
"evidence": ": mod = __import__(import_name) ver = getattr(mod, \"__version__\", \"unknown\")",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "cortex_mcp/scripts/verify_installation.py",
"line": 133,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "initialize_context",
"tags": [],
"reasons": {}
},
{
"tool": "create_branch",
"tags": [],
"reasons": {}
},
{
"tool": "search_context",
"tags": [],
"reasons": {}
},
{
"tool": "update_memory",
"tags": [],
"reasons": {}
},
{
"tool": "get_active_summary",
"tags": [],
"reasons": {}
},
{
"tool": "sync_to_cloud",
"tags": [],
"reasons": {}
},
{
"tool": "sync_from_cloud",
"tags": [],
"reasons": {}
},
{
"tool": "load_context",
"tags": [],
"reasons": {}
},
{
"tool": "get_loaded_contexts",
"tags": [],
"reasons": {}
},
{
"tool": "compress_context",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_context",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_contexts",
"tags": [],
"reasons": {}
},
{
"tool": "accept_suggestions",
"tags": [],
"reasons": {}
},
{
"tool": "reject_suggestions",
"tags": [],
"reasons": {}
},
{
"tool": "record_reference",
"tags": [],
"reasons": {}
},
{
"tool": "update_reference_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "get_reference_statistics",
"tags": [],
"reasons": {}
},
{
"tool": "create_node",
"tags": [],
"reasons": {}
},
{
"tool": "list_nodes",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_node_grouping",
"tags": [],
"reasons": {}
},
{
"tool": "get_hierarchy",
"tags": [],
"reasons": {}
},
{
"tool": "link_git_branch",
"tags": [],
"reasons": {}
},
{
"tool": "get_git_status",
"tags": [],
"reasons": {}
},
{
"tool": "check_git_branch_change",
"tags": [],
"reasons": {}
},
{
"tool": "list_git_links",
"tags": [],
"reasons": {}
},
{
"tool": "unlink_git_branch",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"unlink\" in tool name"
]
}
},
{
"tool": "get_dashboard_url",
"tags": [],
"reasons": {}
},
{
"tool": "create_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "restore_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "list_snapshots",
"tags": [],
"reasons": {}
},
{
"tool": "get_backup_history",
"tags": [],
"reasons": {}
},
{
"tool": "get_automation_status",
"tags": [],
"reasons": {}
},
{
"tool": "record_automation_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "should_confirm_action",
"tags": [],
"reasons": {}
},
{
"tool": "set_automation_mode",
"tags": [],
"reasons": {}
},
{
"tool": "add_semantic_relation",
"tags": [],
"reasons": {}
},
{
"tool": "infer_relations",
"tags": [],
"reasons": {}
},
{
"tool": "detect_conflicts",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_related_contexts",
"tags": [],
"reasons": {}
},
{
"tool": "get_semantic_web_stats",
"tags": [],
"reasons": {}
},
{
"tool": "set_boundary",
"tags": [],
"reasons": {}
},
{
"tool": "infer_boundary",
"tags": [],
"reasons": {}
},
{
"tool": "validate_boundary_action",
"tags": [],
"reasons": {}
},
{
"tool": "get_boundary_protocol",
"tags": [],
"reasons": {}
},
{
"tool": "get_boundary_violations",
"tags": [],
"reasons": {}
},
{
"tool": "clear_boundary",
"tags": [],
"reasons": {}
},
{
"tool": "scan_project_deep",
"tags": [],
"reasons": {}
},
{
"tool": "rescan_project",
"tags": [],
"reasons": {}
},
{
"tool": "get_scan_estimate",
"tags": [],
"reasons": {}
},
{
"tool": "get_context_graph_info",
"tags": [],
"reasons": {}
},
{
"tool": "sync_parallel_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "get_active_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "verify_response",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "eec0a171ccc450255dada9a5e6259138dd597149acb97d33ab0092a3e954e870",
"stats": {
"tools": 53,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 11,
"medium": 3,
"low": 3,
"info": 0
}
}
}