Cleanor — 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": "https://mcp.cleanor.app/mcp",
"source": {
"kind": "http",
"origin": "https://mcp.cleanor.app/mcp"
},
"server": {
"name": "cleanor",
"version": "0.6.0"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "coverage-honesty",
"level": "live",
"label": "inspection depth (live) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.13"
},
"capability": {
"level": "high",
"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)",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)"
],
"tags": [
"untrusted-input",
"external-sink",
"sensitive-source"
]
},
"coverage": {
"level": "live",
"inputs": {
"toolSurface": true,
"implementationSource": false,
"packageMetadata": false,
"liveTransport": true
},
"caveats": []
},
"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: optimize_image ⇒ hmac. Untrusted input is ingested, private data is read, and it can be sent to an external sink — and at least one leg is a direct schema wire (⇒), where a producer's output drops straight into a free-text parameter of the next tool, so the chain needs little agent cooperation. 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": "optimize_image → hmac"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"optimize_image"
],
"sources": [
"hmac"
],
"sinks": [
"hmac"
],
"path": [
"optimize_image",
"hmac"
],
"edges": [
{
"from": "optimize_image",
"to": "hmac",
"kind": "schema-wired"
}
],
"wired": true
}
},
{
"ruleId": "MTC-FLOW-003",
"title": "Read-and-egress in one tool: \"hmac\"",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tool \"hmac\" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.",
"remediation": "Separate reading from sending; require explicit user confirmation before egress of file/secret contents.",
"location": {
"kind": "flow",
"name": "hmac"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"tags": [
"external-sink",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"image_url\" on \"optimize_image\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"optimize_image\" takes a URL/host parameter \"image_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": "optimize_image",
"field": "inputSchema.properties.image_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "image_url"
}
},
{
"ruleId": "MTC-NET-005",
"title": "Remote HTTP MCP endpoint",
"category": "network",
"severity": "info",
"confidence": "strong",
"description": "Remote endpoint mcp.cleanor.app. MCP Trust Checker does not test server-side authentication/authorization; verify the endpoint requires auth.",
"location": {
"kind": "transport"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"optimize_image"
],
"sensitiveSource": [
"hmac"
],
"externalSink": [
"hmac"
],
"selfContained": false,
"path": [
"optimize_image",
"hmac"
],
"pathWired": true,
"description": "A cross-tool exfiltration chain exists: optimize_image ⇒ hmac."
},
{
"id": "flow-2",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"hmac"
],
"externalSink": [
"hmac"
],
"selfContained": true,
"description": "Tool \"hmac\" both reads sensitive data and can send it externally."
}
],
"capabilities": [
{
"tool": "optimize_image",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "storage_capacity",
"tags": [],
"reasons": {}
},
{
"tool": "image_format_savings",
"tags": [],
"reasons": {}
},
{
"tool": "qr_code",
"tags": [],
"reasons": {}
},
{
"tool": "hash",
"tags": [],
"reasons": {}
},
{
"tool": "uuid",
"tags": [],
"reasons": {}
},
{
"tool": "base64",
"tags": [],
"reasons": {}
},
{
"tool": "json_format",
"tags": [],
"reasons": {}
},
{
"tool": "jwt_decode",
"tags": [],
"reasons": {}
},
{
"tool": "color",
"tags": [],
"reasons": {}
},
{
"tool": "slugify",
"tags": [],
"reasons": {}
},
{
"tool": "count",
"tags": [],
"reasons": {}
},
{
"tool": "regex_test",
"tags": [],
"reasons": {}
},
{
"tool": "cron_describe",
"tags": [],
"reasons": {}
},
{
"tool": "unit_convert",
"tags": [],
"reasons": {}
},
{
"tool": "datetime",
"tags": [],
"reasons": {}
},
{
"tool": "url_parse",
"tags": [],
"reasons": {}
},
{
"tool": "base_convert",
"tags": [],
"reasons": {}
},
{
"tool": "diff",
"tags": [],
"reasons": {}
},
{
"tool": "hmac",
"tags": [
"external-sink",
"sensitive-source"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
],
"sensitive-source": [
"parameter \"secret\""
]
}
},
{
"tool": "placeholder_image",
"tags": [],
"reasons": {}
},
{
"tool": "color_palette",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "081c96c0b2266818e01d9c8383ee21e4b593ddcc693ef098b01b956408777a85",
"stats": {
"tools": 22,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 1,
"medium": 1,
"low": 0,
"info": 1
}
}
}