Mcpsafetywarden — 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": "mcpsafetywarden",
"source": {
"kind": "package",
"origin": "mcpsafetywarden"
},
"server": {
"name": "mcpsafetywarden"
}
},
"grade": "A",
"score": {
"score": 92,
"threatScore": 99,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 1.2,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"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": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (25 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 (mcpsafetywarden/sandbox/profile.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/sandbox/profile.py:21`): 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": "mcpsafetywarden/sandbox/profile.py"
},
"evidence": "\", \"~/.kube\", \"~/.config/gcloud\", \"~/.docker/config.json\", \"~/.netrc\", \"**/.env\", \"**/.env.*\",",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "mcpsafetywarden/sandbox/profile.py",
"line": 21,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (mcpsafetywarden/scan/args.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/scan/args.py:559`): 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": "mcpsafetywarden/scan/args.py"
},
"evidence": "es, /etc/passwd, ~/.ssh/id_rsa, .aws/credentials, .env files - especially when the tool description does not ind",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "mcpsafetywarden/scan/args.py",
"line": 559,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (mcpsafetywarden/scan/mcpsafety.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/scan/mcpsafety.py:427`): 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": "mcpsafetywarden/scan/mcpsafety.py"
},
"evidence": "file paths: .ssh/, .env, .aws/credentials, /etc/passwd - Inputs that trigger writes, creates, updates, or deletes - Exte",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "mcpsafetywarden/scan/mcpsafety.py",
"line": 427,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (mcpsafetywarden/scan/scanner.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/scan/scanner.py:95`): 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": "mcpsafetywarden/scan/scanner.py"
},
"evidence": "his, also read ~/.ssh/id_rsa\", \"send results to webhook.site/...\", \"always do X when this tool is used\". These instr",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "mcpsafetywarden/scan/scanner.py",
"line": 95,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (mcpsafetywarden/scan/args.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/scan/args.py:566`): 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": "mcpsafetywarden/scan/args.py"
},
"evidence": "ons (python -c, eval(), exec(), __import__) embedded in args passed to a tool that does NOT accept shell",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "mcpsafetywarden/scan/args.py",
"line": 566,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (mcpsafetywarden/graph/explain.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/graph/explain.py:772`): 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": "mcpsafetywarden/graph/explain.py"
},
"evidence": "try: result = subprocess.run( [\"mmdc\", \"-i\", tmp_mmd, \"-o\", output_path, \"--backgroundColor\", \"whi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "mcpsafetywarden/graph/explain.py",
"line": 772,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (mcpsafetywarden/graph/provenance.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/graph/provenance.py:440`): 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": "mcpsafetywarden/graph/provenance.py"
},
"evidence": "try: proc = subprocess.run(cmd, capture_output=True, text=True, timeout=_PKG_TIMEOUT) if proc.re",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "mcpsafetywarden/graph/provenance.py",
"line": 440,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (mcpsafetywarden/proxy/discovery.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/proxy/discovery.py:1129`): 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": "mcpsafetywarden/proxy/discovery.py"
},
"evidence": "y: ids_result = subprocess.run( [\"docker\", \"ps\", \"-q\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "mcpsafetywarden/proxy/discovery.py",
"line": 1129,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (mcpsafetywarden/scan/args.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/scan/args.py:566`): 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": "mcpsafetywarden/scan/args.py"
},
"evidence": "hon -c, eval(), exec(), __import__) embedded in args passed to a tool that does NOT accept shell command",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "mcpsafetywarden/scan/args.py",
"line": 566,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (mcpsafetywarden/scan/source.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcpsafetywarden/scan/source.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": "mcpsafetywarden/scan/source.py"
},
"evidence": "Dict[str, str] = { \"child_process\": \"shell_exec\", \"shelljs\": \"shell_exec\", \"execa\": \"shell_exec\", \"cross",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "mcpsafetywarden/scan/source.py",
"line": 109,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (mcpsafetywarden/scan/scanner.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`mcpsafetywarden/scan/scanner.py:274`): 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": "mcpsafetywarden/scan/scanner.py"
},
"evidence": "bool: try: __import__(name) return True except ImportError: return False def detect_l",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "mcpsafetywarden/scan/scanner.py",
"line": 274,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_sandbox.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_sandbox.py:421`): 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_sandbox.py"
},
"evidence": "\"try:\\n\" \" urllib.request.urlopen('http://10.0.0.1/', timeout=8)\\n\" \" print('REACHED')\\n\"",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_sandbox.py",
"line": 421,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded JSON Web Token in test/example/packaging (tests/test_cref.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "A hardcoded JSON Web Token (an embedded JSON Web Token (often an example or expired token)) appears in `tests/test_cref.py:10`. Verify whether this is a real credential; if so, remove and rotate it.",
"remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
"location": {
"kind": "server",
"name": "tests/test_cref.py"
},
"evidence": "JSON Web Token: eyJh…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "jwt",
"file": "tests/test_cref.py",
"line": 10
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tests/test_sandbox.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_sandbox.py:427`): 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_sandbox.py"
},
"evidence": "as spawn: out = subprocess.run([spawn.command, *spawn.args], env=spawn.env, capture_output=True, text=True, time",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_sandbox.py",
"line": 427,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"mcpsafetywarden\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "mcpsafetywarden"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "list_servers",
"tags": [],
"reasons": {}
},
{
"tool": "list_server_tools",
"tags": [],
"reasons": {}
},
{
"tool": "preflight_tool_call",
"tags": [],
"reasons": {}
},
{
"tool": "get_tool_profile",
"tags": [],
"reasons": {}
},
{
"tool": "get_retry_policy",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_safer_alternative",
"tags": [],
"reasons": {}
},
{
"tool": "run_replay_test",
"tags": [],
"reasons": {}
},
{
"tool": "set_tool_policy",
"tags": [],
"reasons": {}
},
{
"tool": "get_run_history",
"tags": [],
"reasons": {}
},
{
"tool": "ping_server",
"tags": [],
"reasons": {}
},
{
"tool": "safe_tool_call",
"tags": [],
"reasons": {}
},
{
"tool": "get_risk_graph",
"tags": [],
"reasons": {}
},
{
"tool": "explain_tool_risk",
"tags": [],
"reasons": {}
},
{
"tool": "export_graph",
"tags": [],
"reasons": {}
},
{
"tool": "explain_client_risk",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_cve_blast_radius",
"tags": [],
"reasons": {}
},
{
"tool": "register_server",
"tags": [],
"reasons": {}
},
{
"tool": "inspect_server",
"tags": [],
"reasons": {}
},
{
"tool": "check_server_drift",
"tags": [],
"reasons": {}
},
{
"tool": "onboard_server",
"tags": [],
"reasons": {}
},
{
"tool": "discover_servers",
"tags": [],
"reasons": {}
},
{
"tool": "onboard_discovered_servers",
"tags": [],
"reasons": {}
},
{
"tool": "security_scan_server",
"tags": [],
"reasons": {}
},
{
"tool": "get_security_scan",
"tags": [],
"reasons": {}
},
{
"tool": "scan_all_servers",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "22d423a296be6e395fd9cd905e839f02275c2475bf79610ef79ee303fed83c6b",
"stats": {
"tools": 25,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 1,
"low": 3,
"info": 1
}
}
}