Neurostack — 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": "neurostack",
"source": {
"kind": "package",
"origin": "neurostack"
},
"server": {
"name": "neurostack"
}
},
"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 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": [
"sensitive-source",
"file-write",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (24 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 (npm/bin/neurostack.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`npm/bin/neurostack.js:4`): 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": "npm/bin/neurostack.js"
},
"evidence": ", execSync } = require(\"child_process\"); const fs = require(\"fs\"); const path = require(\"path\"); const os = require(\"os\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "npm/bin/neurostack.js",
"line": 4,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/neurostack/brief.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/neurostack/brief.py:56`): 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/neurostack/brief.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"log\", f\"--max-count={limit}\", \"--oneline\", \"--no-decorate\"]",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/neurostack/brief.py",
"line": 56,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/neurostack/cli/sessions.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/neurostack/cli/sessions.py:250`): 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/neurostack/cli/sessions.py"
},
"evidence": "rs.target \"\"\" ) subprocess.run( [\"systemctl\", \"--user\", \"daemon-reload\"], check=False, capture_o",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/neurostack/cli/sessions.py",
"line": 250,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/neurostack/cli/setup.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/neurostack/cli/setup.py:33`): 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/neurostack/cli/setup.py"
},
"evidence": "y: result = subprocess.run( [nvidia_smi, \"--query-gpu=name,memory.total\", \"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/neurostack/cli/setup.py",
"line": 33,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/neurostack/cli/utils.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/neurostack/cli/utils.py:49`): 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/neurostack/cli/utils.py"
},
"evidence": "try: result = subprocess.run( [fuser, db_path], capture_output=True, text=True, timeou",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/neurostack/cli/utils.py",
"line": 49,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/neurostack/tools/file_tools.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/neurostack/tools/file_tools.py:159`): 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/neurostack/tools/file_tools.py"
},
"evidence": "etedProcess: return subprocess.run( [\"git\", *args], cwd=str(cwd), check=check, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/neurostack/tools/file_tools.py",
"line": 159,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"vault_write_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"vault_write_file\" can write, overwrite or delete files (keyword \"write_file\" 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": "vault_write_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"vault_delete_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"vault_delete_file\" can write, overwrite or delete files (keyword \"delete_file\" 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": "vault_delete_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (npm/bin/neurostack.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`npm/bin/neurostack.js:29`): 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": "npm/bin/neurostack.js"
},
"evidence": "nc(preuninstall)) { require(preuninstall); } console.log(\" \\x1b[36m▸\\x1b[0m Removing npm package...\\n\"); try",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "npm/bin/neurostack.js",
"line": 29,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"vault_write_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vault_write_file\" 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": "vault_write_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"vault_delete_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"vault_delete_file\" 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": "vault_delete_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (npm/postinstall.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`npm/postinstall.js:4`): 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": "npm/postinstall.js"
},
"evidence": "{ execSync } = require(\"child_process\"); const fs = require(\"fs\"); const path = require(\"path\"); const os = require(\"os\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "npm/postinstall.js",
"line": 4,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_file_tools.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_file_tools.py:38`): 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_file_tools.py"
},
"evidence": "etedProcess: return subprocess.run( [\"git\", *args], cwd=str(cwd), check=check, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_file_tools.py",
"line": 38,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"neurostack\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "neurostack"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "vault_read_file",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "vault_list_files",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "vault_write_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"write_file\" in tool name"
]
}
},
{
"tool": "vault_delete_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"delete_file\" in tool name"
]
}
},
{
"tool": "session_brief",
"tags": [],
"reasons": {}
},
{
"tool": "vault_context",
"tags": [],
"reasons": {}
},
{
"tool": "vault_remember",
"tags": [],
"reasons": {}
},
{
"tool": "vault_forget",
"tags": [],
"reasons": {}
},
{
"tool": "vault_update_memory",
"tags": [],
"reasons": {}
},
{
"tool": "vault_merge",
"tags": [],
"reasons": {}
},
{
"tool": "vault_memories",
"tags": [],
"reasons": {}
},
{
"tool": "vault_search",
"tags": [],
"reasons": {}
},
{
"tool": "vault_ask",
"tags": [],
"reasons": {}
},
{
"tool": "vault_summary",
"tags": [],
"reasons": {}
},
{
"tool": "vault_graph",
"tags": [],
"reasons": {}
},
{
"tool": "vault_related",
"tags": [],
"reasons": {}
},
{
"tool": "vault_triples",
"tags": [],
"reasons": {}
},
{
"tool": "vault_communities",
"tags": [],
"reasons": {}
},
{
"tool": "vault_stats",
"tags": [],
"reasons": {}
},
{
"tool": "vault_record_usage",
"tags": [],
"reasons": {}
},
{
"tool": "vault_prediction_errors",
"tags": [],
"reasons": {}
},
{
"tool": "vault_session_start",
"tags": [],
"reasons": {}
},
{
"tool": "vault_session_end",
"tags": [],
"reasons": {}
},
{
"tool": "vault_harvest",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "7ee538e67b31dbb87836cf7c319c58fd284f955ec3d4ee30585b7065b490a246",
"stats": {
"tools": 24,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 3,
"low": 4,
"info": 1
}
}
}