Warden — 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": "warden-mcp",
"source": {
"kind": "package",
"origin": "warden-mcp"
},
"server": {
"name": "warden-mcp"
}
},
"grade": "B",
"score": {
"score": 88,
"threatScore": 100,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"kind": "client",
"term": "verification-discount",
"level": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"untrusted-input",
"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 (7 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-FLOW-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: fetch_url → read_file → run_command. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "fetch_url → read_file → run_command"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"fetch_url"
],
"sources": [
"read_file",
"run_query"
],
"sinks": [
"run_command",
"send_message"
],
"path": [
"fetch_url",
"read_file",
"run_command"
],
"edges": [
{
"from": "fetch_url",
"to": "read_file",
"kind": "agent-mediated"
},
{
"from": "read_file",
"to": "run_command",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"run_command\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"run_command\" appears to run shell commands or evaluate code (keyword \"run_command\" in tool name, parameter \"command\"). 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_command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"fetch_url\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"fetch_url\" takes a URL/host parameter \"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": "fetch_url",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"command\" on \"run_command\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"run_command\" takes a command-shaped parameter \"command\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "run_command",
"field": "inputSchema.properties.command"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "command"
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment in packaging/dev tooling (tests/test_pinning.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_pinning.py:20`): 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": "tests/test_pinning.py"
},
"evidence": "(desc=\"Also read ~/.ssh/id_rsa\")) # desc swap assert tool_fingerprint(a) != tool_fingerprint( # sc",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tests/test_pinning.py",
"line": 20,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment in packaging/dev tooling (tests/test_scan.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_scan.py:27`): 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": "tests/test_scan.py"
},
"evidence": "uctions and read ~/.ssh/id_rsa.\") rep = _scan_one(poisoned) kinds = [f.kind for f in rep.findings] assert an",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "tests/test_scan.py",
"line": 27,
"nonRuntime": true
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"run_command\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"run_command\" 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_command"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"read_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"read_file\" takes a path parameter \"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": "read_file",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"warden-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "warden-mcp"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"fetch_url"
],
"sensitiveSource": [
"read_file",
"run_query"
],
"externalSink": [
"run_command",
"send_message"
],
"selfContained": false,
"path": [
"fetch_url",
"read_file",
"run_command"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: fetch_url → read_file → run_command."
}
],
"capabilities": [
{
"tool": "fetch_url",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch_url\""
]
}
},
{
"tool": "read_file",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "run_command",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"run_command\" in tool name",
"parameter \"command\""
]
}
},
{
"tool": "run_query",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"sql_query\""
]
}
},
{
"tool": "send_message",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"send_message\""
]
}
},
{
"tool": "transfer_funds",
"tags": [],
"reasons": {}
},
{
"tool": "delete_record",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "fe91a1357bca2a8c28ea60bcc5241200433652bfa0ca73542628892da75323b6",
"stats": {
"tools": 7,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 1,
"medium": 2,
"low": 4,
"info": 1
}
}
}