InsideOut (Riley) — 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://app.luthersystems.com/v1/insideout-mcp",
"source": {
"kind": "http",
"origin": "https://app.luthersystems.com/v1/insideout-mcp"
},
"server": {
"name": "insideout-agent",
"version": "v2.0.0"
}
},
"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: awsinspect_batch → tflogs → tfgenerate. 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": "awsinspect_batch → tflogs → tfgenerate"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"awsinspect_batch",
"gcpinspect_batch",
"tfgenerate",
"tflogs"
],
"sources": [
"tflogs"
],
"sinks": [
"tfgenerate"
],
"path": [
"awsinspect_batch",
"tflogs",
"tfgenerate"
],
"edges": [
{
"from": "awsinspect_batch",
"to": "tflogs",
"kind": "agent-mediated"
},
{
"from": "tflogs",
"to": "tfgenerate",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-CAP-004",
"title": "Open-world tool \"tflogs\" also reads sensitive data",
"category": "exfiltration",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"tflogs\" declares openWorldHint=true — it interacts with entities outside the trust boundary — while also reading sensitive data. That combination is a canonical lethal-trifecta indicator.",
"remediation": "Separate outward-facing tools from sensitive-data reads; require confirmation between them.",
"location": {
"kind": "tool",
"name": "tflogs"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"tags": [
"untrusted-input",
"sensitive-source"
]
}
},
{
"ruleId": "MTC-NET-005",
"title": "Remote HTTP MCP endpoint",
"category": "network",
"severity": "info",
"confidence": "strong",
"description": "Remote endpoint app.luthersystems.com. 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": [
"awsinspect_batch",
"gcpinspect_batch",
"tfgenerate",
"tflogs"
],
"sensitiveSource": [
"tflogs"
],
"externalSink": [
"tfgenerate"
],
"selfContained": false,
"path": [
"awsinspect_batch",
"tflogs",
"tfgenerate"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: awsinspect_batch → tflogs → tfgenerate."
}
],
"capabilities": [
{
"tool": "awsinspect",
"tags": [],
"reasons": {}
},
{
"tool": "awsinspect_batch",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "convoawait",
"tags": [],
"reasons": {}
},
{
"tool": "convoinspect",
"tags": [],
"reasons": {}
},
{
"tool": "convoopen",
"tags": [],
"reasons": {}
},
{
"tool": "convoreply",
"tags": [],
"reasons": {}
},
{
"tool": "convostatus",
"tags": [],
"reasons": {}
},
{
"tool": "credawait",
"tags": [],
"reasons": {}
},
{
"tool": "gcpinspect",
"tags": [],
"reasons": {}
},
{
"tool": "gcpinspect_batch",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "help",
"tags": [],
"reasons": {}
},
{
"tool": "stackdiff",
"tags": [],
"reasons": {}
},
{
"tool": "stackrollback",
"tags": [],
"reasons": {}
},
{
"tool": "stackversions",
"tags": [],
"reasons": {}
},
{
"tool": "submit_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "tfdeploy",
"tags": [],
"reasons": {}
},
{
"tool": "tfdestroy",
"tags": [],
"reasons": {}
},
{
"tool": "tfdrift",
"tags": [],
"reasons": {}
},
{
"tool": "tfgenerate",
"tags": [
"untrusted-input",
"external-sink"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
],
"external-sink": [
"keyword \"curl\""
]
}
},
{
"tool": "tflogs",
"tags": [
"untrusted-input",
"sensitive-source"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
],
"sensitive-source": [
"keyword \"get_logs\""
]
}
},
{
"tool": "tfoutputs",
"tags": [],
"reasons": {}
},
{
"tool": "tfplan",
"tags": [],
"reasons": {}
},
{
"tool": "tfruns",
"tags": [],
"reasons": {}
},
{
"tool": "tfstatus",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "8eff6c62af204b3c474670519c9f487d5b2249f49705a60bf5be0aff8f7dddfa",
"stats": {
"tools": 24,
"prompts": 1,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 0,
"medium": 1,
"low": 0,
"info": 1
}
}
}