Mysql Apifox — 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": "mcp-mysql-apifox",
"source": {
"kind": "package",
"origin": "mcp-mysql-apifox"
},
"server": {
"name": "mcp-mysql-apifox"
}
},
"grade": "B",
"score": {
"score": 83,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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": "critical",
"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)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"sensitive-source",
"untrusted-input",
"external-sink",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (7 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: download_apis → execute_mysql_only → run_curl. 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": "download_apis → execute_mysql_only → run_curl"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"download_apis"
],
"sources": [
"execute_mysql_only",
"execute_mysql_readonly"
],
"sinks": [
"run_curl"
],
"path": [
"download_apis",
"execute_mysql_only",
"run_curl"
],
"edges": [
{
"from": "download_apis",
"to": "execute_mysql_only",
"kind": "agent-mediated"
},
{
"from": "execute_mysql_only",
"to": "run_curl",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/native-prompt/dist/lib/platforms/darwin.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/native-prompt/dist/lib/platforms/darwin.js:2`): 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": "src/native-prompt/dist/lib/platforms/darwin.js"
},
"evidence": "\"use strict\"; var child_process_1 = require(\"child_process\"); var path_1 = require(\"path\"); module.exports = fun",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/native-prompt/dist/lib/platforms/darwin.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/native-prompt/dist/lib/platforms/linux.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/native-prompt/dist/lib/platforms/linux.js:2`): 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": "src/native-prompt/dist/lib/platforms/linux.js"
},
"evidence": "\"use strict\"; var child_process_1 = require(\"child_process\"); var path_1 = require(\"path\"); module.exports = fun",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/native-prompt/dist/lib/platforms/linux.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/native-prompt/dist/lib/platforms/win32.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/native-prompt/dist/lib/platforms/win32.js:4`): 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": "src/native-prompt/dist/lib/platforms/win32.js"
},
"evidence": "splayBox = void 0; var child_process_1 = require(\"child_process\"); var path_1 = require(\"path\"); function displayBox(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/native-prompt/dist/lib/platforms/win32.js",
"line": 4,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/terminal-input.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/terminal-input.js:1`): 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": "src/terminal-input.js"
},
"evidence": "st { spawn } = require('child_process'); const os = require('os'); class TerminalInput { constructor() { th",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/terminal-input.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/server.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/server.js:770`): 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": "src/server.js"
},
"evidence": "const response = await axios.post( `https://api.apifox.com/v1/projects/${projectId}/export-openapi",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/server.js",
"line": 770,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/terminal-input.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/terminal-input.js:177`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "src/terminal-input.js"
},
"evidence": "equire('child_process').execSync(`which ${command}`, { stdio: 'ignore' }); return true; } catch (err",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/terminal-input.js",
"line": 177,
"nonRuntime": false
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"download_apis"
],
"sensitiveSource": [
"execute_mysql_only",
"execute_mysql_readonly"
],
"externalSink": [
"run_curl"
],
"selfContained": false,
"path": [
"download_apis",
"execute_mysql_only",
"run_curl"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: download_apis → execute_mysql_only → run_curl."
}
],
"capabilities": [
{
"tool": "execute_mysql_only",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"sql\""
]
}
},
{
"tool": "execute_mysql_readonly",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"parameter \"sql\""
]
}
},
{
"tool": "get_tables_info",
"tags": [],
"reasons": {}
},
{
"tool": "get_connection_status",
"tags": [],
"reasons": {}
},
{
"tool": "import_openapi",
"tags": [],
"reasons": {}
},
{
"tool": "download_apis",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "run_curl",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"curl\""
]
}
}
],
"surfaceDigest": "6c705e69d67542dc88a59581a29e7c0c309ebb4399d0e7a6395db8d9b2423649",
"stats": {
"tools": 7,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 4,
"medium": 2,
"low": 0,
"info": 0
}
}
}