Noelclaw — 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": "@noelclaw/mcp",
"source": {
"kind": "package",
"origin": "@noelclaw/mcp"
},
"server": {
"name": "@noelclaw/mcp"
}
},
"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": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli.js:47`): 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/cli.js"
},
"evidence": "clink-input.js\"); const child_process = __importStar(require(\"child_process\")); (0, config_js_1.hydrateEnvFromConfig)();",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli.js",
"line": 47,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/agent-loop.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/agent-loop.js:61`): 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-loop.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-loop.js",
"line": 61,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/cli.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli.js:496`): 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/cli.js"
},
"evidence": "const res = await fetch(\"https://registry.npmjs.org/@noelclaw/mcp/latest\", { signal: AbortSignal.timeo",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/cli.js",
"line": 496,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/enrichment-router.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/enrichment-router.js:85`): 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/enrichment-router.js"
},
"evidence": "const res = await fetch(`https://api.llama.fi/protocol/${slug}`, { signal: AbortSignal.timeout(8000) });",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/enrichment-router.js",
"line": 85,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/index.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:87`): 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/index.js"
},
"evidence": "const res = await fetch(\"https://registry.npmjs.org/@noelclaw/mcp/latest\", { signal: AbortSignal.timeo",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/index.js",
"line": 87,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/tools/base-mcp.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/base-mcp.js:166`): 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/tools/base-mcp.js"
},
"evidence": "ss, \"latest\"]), fetch(\"https://api.coingecko.com/api/v3/simple/price?ids=ethereum&vs_currencies=usd\", {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/tools/base-mcp.js",
"line": 166,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/tools/base.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/base.js:168`): 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/tools/base.js"
},
"evidence": "ch(() => null), fetch(\"https://api.coingecko.com/api/v3/simple/price?ids=ethereum&vs_currencies=usd\", {",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/tools/base.js",
"line": 168,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/tools/defi.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/defi.js:231`): 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/tools/defi.js"
},
"evidence": "const res = await fetch(\"https://yields.llama.fi/pools\", { signal: AbortSignal.timeout(15000) });",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/tools/defi.js",
"line": 231,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/tools/equity.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/equity.js:151`): 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/tools/equity.js"
},
"evidence": "const res = await fetch(`https://query1.finance.yahoo.com/v8/finance/chart/${encodeURIComponent(ticker)}?interval=",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/tools/equity.js",
"line": 151,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/tools/insight.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/insight.js:191`): 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/tools/insight.js"
},
"evidence": "const res = await fetch(`https://api.coingecko.com/api/v3/search?query=${encodeURIComponent(token)}`, { signal: Ab",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/tools/insight.js",
"line": 191,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (dist/tools/rh-bridge.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/tools/rh-bridge.js:48`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/tools/rh-bridge.js"
},
"evidence": "const res = await fetch(`https://query1.finance.yahoo.com/v8/finance/chart/${encodeURIComponent(symbol)}?interval=",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "dist/tools/rh-bridge.js",
"line": 48,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "78b6b650c9a52258ee013d32af21be489cbda04e687f69ed9165db1b7c6cdd80",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 10,
"low": 0,
"info": 0
}
}
}