Telekash — 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": "telekash-mcp-server",
"source": {
"kind": "package",
"origin": "telekash-mcp-server"
},
"server": {
"name": "telekash-mcp-server"
}
},
"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": [
"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": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (29 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: list_markets → export_data → delete_alert. 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": "list_markets → export_data → delete_alert"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"list_markets"
],
"sources": [
"export_data"
],
"sinks": [
"register_alert",
"delete_alert"
],
"path": [
"list_markets",
"export_data",
"delete_alert"
],
"edges": [
{
"from": "list_markets",
"to": "export_data",
"kind": "agent-mediated"
},
{
"from": "export_data",
"to": "delete_alert",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/broker.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/broker.js:346`): 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": "dist/broker.js"
},
"evidence": "const response = await fetch(\"https://clob.polymarket.com/time\"); if (response.ok) {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/broker.js",
"line": 346,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/x402.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/x402.js:221`): 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": "dist/x402.js"
},
"evidence": "const response = await fetch(`https://api.stripe.com/v1/payment_intents/${piId}`, { headers: {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/x402.js",
"line": 221,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"callback_url\" on \"register_alert\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"register_alert\" takes a URL/host parameter \"callback_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": "register_alert",
"field": "inputSchema.properties.callback_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "callback_url"
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/openbb-connector.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/openbb-connector.py:59`): 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": "examples/openbb-connector.py"
},
"evidence": "} proc = subprocess.Popen( self._server_cmd, stdin=subprocess.PIPE, s",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/openbb-connector.py",
"line": 59,
"nonRuntime": true
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"list_markets"
],
"sensitiveSource": [
"export_data"
],
"externalSink": [
"register_alert",
"delete_alert"
],
"selfContained": false,
"path": [
"list_markets",
"export_data",
"delete_alert"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: list_markets → export_data → delete_alert."
}
],
"capabilities": [
{
"tool": "get_probability",
"tags": [],
"reasons": {}
},
{
"tool": "list_markets",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"browse\""
]
}
},
{
"tool": "get_history",
"tags": [],
"reasons": {}
},
{
"tool": "search_markets",
"tags": [],
"reasons": {}
},
{
"tool": "get_sentiment",
"tags": [],
"reasons": {}
},
{
"tool": "get_market_stats",
"tags": [],
"reasons": {}
},
{
"tool": "get_trending",
"tags": [],
"reasons": {}
},
{
"tool": "compare_sources",
"tags": [],
"reasons": {}
},
{
"tool": "detect_arbitrage",
"tags": [],
"reasons": {}
},
{
"tool": "get_signal",
"tags": [],
"reasons": {}
},
{
"tool": "track_prediction",
"tags": [],
"reasons": {}
},
{
"tool": "get_performance",
"tags": [],
"reasons": {}
},
{
"tool": "get_divergences",
"tags": [],
"reasons": {}
},
{
"tool": "get_edge",
"tags": [],
"reasons": {}
},
{
"tool": "create_market",
"tags": [],
"reasons": {}
},
{
"tool": "generate_api_key",
"tags": [],
"reasons": {}
},
{
"tool": "get_usage",
"tags": [],
"reasons": {}
},
{
"tool": "register_alert",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
]
}
},
{
"tool": "list_alerts",
"tags": [],
"reasons": {}
},
{
"tool": "delete_alert",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"webhook\""
]
}
},
{
"tool": "execute_trade",
"tags": [],
"reasons": {}
},
{
"tool": "get_order_status",
"tags": [],
"reasons": {}
},
{
"tool": "cancel_order",
"tags": [],
"reasons": {}
},
{
"tool": "get_pool_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_agent_balance",
"tags": [],
"reasons": {}
},
{
"tool": "get_resolution_status",
"tags": [],
"reasons": {}
},
{
"tool": "export_data",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"export_data\""
]
}
},
{
"tool": "get_health",
"tags": [],
"reasons": {}
},
{
"tool": "get_calibration_changelog",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d450dd7dbf817e588c22e1433606a78082d74c1658871731ba7143181d88ddd0",
"stats": {
"tools": 29,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 0,
"medium": 3,
"low": 1,
"info": 0
}
}
}