Kansei Link — 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": "@kansei-link/mcp-server",
"source": {
"kind": "package",
"origin": "@kansei-link/mcp-server"
},
"server": {
"name": "@kansei-link/mcp-server"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"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 (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-SRC-002",
"title": "Shell/command execution in server code (dist/crawler/mine-issues.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/crawler/mine-issues.js:15`): 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": "dist/crawler/mine-issues.js"
},
"evidence": "{ execSync } from \"node:child_process\"; async function main() { const args = process.argv.slice(2); // Parse CLI",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/crawler/mine-issues.js",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/crawler/ops-cycle.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/crawler/ops-cycle.js:17`): 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": "dist/crawler/ops-cycle.js"
},
"evidence": "{ execSync } from \"node:child_process\"; import { resolve } from \"node:path\"; const ROOT = resolve(import.meta.dirname, \"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/crawler/ops-cycle.js",
"line": 17,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/agent-army/adapters.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/agent-army/adapters.js:14`): 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/agent-army/adapters.js"
},
"evidence": "const res = await fetch(\"https://api.anthropic.com/v1/messages\", { method: \"POST\", headers",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/agent-army/adapters.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/auth.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/auth.js:46`): 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/auth.js"
},
"evidence": "const res = await fetch(\"https://api.resend.com/emails\", { method: \"POST\", headers: {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/auth.js",
"line": 46,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/crawler/pipeline/enrich.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/crawler/pipeline/enrich.js:9`): 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/crawler/pipeline/enrich.js"
},
"evidence": "; const res = await fetch(`https://api.github.com/repos/${repoFullName}`, { headers }); if (!res.ok) ret",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/crawler/pipeline/enrich.js",
"line": 9,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/crawler/refresh.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/crawler/refresh.js:30`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/crawler/refresh.js"
},
"evidence": "; const res = await fetch(`https://api.github.com/repos/${repoFullName}`, { headers }); if (!res.ok) ret",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/crawler/refresh.js",
"line": 30,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/crawler/sources/github-issues.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/crawler/sources/github-issues.js:147`): 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/crawler/sources/github-issues.js"
},
"evidence": "const cRes = await fetch(`https://api.github.com/repos/${target.repo}/issues/${issue.number}/comments?per_page=10`,",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/crawler/sources/github-issues.js",
"line": 147,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/http-server.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/http-server.js:763`): 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/http-server.js"
},
"evidence": "const resp = await fetch(\"https://api.sendgrid.com/v3/mail/send\", { method: \"POST\", headers",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/http-server.js",
"line": 763,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"@kansei-link/mcp-server\" 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": "@kansei-link/mcp-server"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "agent_voice",
"tags": [],
"reasons": {}
},
{
"tool": "read_agent_voices",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_token_savings",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "analyze",
"tags": [],
"reasons": {}
},
{
"tool": "audit_cost",
"tags": [],
"reasons": {}
},
{
"tool": "check_updates",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate_design",
"tags": [],
"reasons": {}
},
{
"tool": "find_combinations",
"tags": [],
"reasons": {}
},
{
"tool": "generate_aeo_article",
"tags": [],
"reasons": {}
},
{
"tool": "generate_aeo_report",
"tags": [],
"reasons": {}
},
{
"tool": "get_insights",
"tags": [],
"reasons": {}
},
{
"tool": "get_inspection_queue",
"tags": [],
"reasons": {}
},
{
"tool": "get_recipe",
"tags": [],
"reasons": {}
},
{
"tool": "get_service_detail",
"tags": [],
"reasons": {}
},
{
"tool": "get_service_history",
"tags": [],
"reasons": {}
},
{
"tool": "get_service_tips",
"tags": [],
"reasons": {}
},
{
"tool": "inspect",
"tags": [],
"reasons": {}
},
{
"tool": "lookup",
"tags": [],
"reasons": {}
},
{
"tool": "propose_update",
"tags": [],
"reasons": {}
},
{
"tool": "review_update",
"tags": [],
"reasons": {}
},
{
"tool": "list_pending_updates",
"tags": [],
"reasons": {}
},
{
"tool": "record_event",
"tags": [],
"reasons": {}
},
{
"tool": "report_outcome",
"tags": [],
"reasons": {}
},
{
"tool": "report",
"tags": [],
"reasons": {}
},
{
"tool": "search_services",
"tags": [],
"reasons": {}
},
{
"tool": "submit_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "read_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "submit_inspection",
"tags": [],
"reasons": {}
},
{
"tool": "take_snapshot",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "7230013a291e144d0a9dcc8ccb805910164723b6bf79da9b62d6016651ecb2c3",
"stats": {
"tools": 29,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 6,
"low": 0,
"info": 1
}
}
}