Codeguard — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "codeguard-mcp",
"source": {
"kind": "package",
"origin": "codeguard-mcp"
},
"server": {
"name": "codeguard-mcp"
}
},
"grade": "A",
"score": {
"score": 91,
"threatScore": 99,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 1.2,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"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-1.9"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (5 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-001",
"title": "Dynamic code execution in server code (dist/scanners/vulnerability-scanner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/scanners/vulnerability-scanner.js:86`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/scanners/vulnerability-scanner.js"
},
"evidence": "Deserialization: Using eval() is extremely dangerous', severity: 'critical', cwe: 'CWE-",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/scanners/vulnerability-scanner.js",
"line": 86,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (dist/utils/security-scorer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/utils/security-scorer.js:94`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/utils/security-scorer.js"
},
"evidence": "explanation: 'Never use eval(). Use JSON.parse with proper error handling and validation', tips: [",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "dist/utils/security-scorer.js",
"line": 94,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/scanners/vulnerability-scanner.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scanners/vulnerability-scanner.ts:93`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/scanners/vulnerability-scanner.ts"
},
"evidence": "Deserialization: Using eval() is extremely dangerous', severity: 'critical' as SeverityLevel, cwe: 'C",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/scanners/vulnerability-scanner.ts",
"line": 93,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/utils/security-scorer.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/utils/security-scorer.ts:102`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/utils/security-scorer.ts"
},
"evidence": "explanation: 'Never use eval(). Use JSON.parse with proper error handling and validation', tips: [ '",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/utils/security-scorer.ts",
"line": 102,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/scanners/vulnerability-scanner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/scanners/vulnerability-scanner.js:52`): 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/scanners/vulnerability-scanner.js"
},
"evidence": "ng template literals in exec()', severity: 'critical', cwe: 'CWE-78', ow",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/scanners/vulnerability-scanner.js",
"line": 52,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/utils/security-scorer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/utils/security-scorer.js:73`): 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/utils/security-scorer.js"
},
"evidence": "nimport { spawn } from 'child_process';\\nconst child = spawn('command', [arg1, arg2]);`, explanation: 's",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/utils/security-scorer.js",
"line": 73,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/scanners/vulnerability-scanner.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/scanners/vulnerability-scanner.ts:57`): 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/scanners/vulnerability-scanner.ts"
},
"evidence": "ng template literals in exec()', severity: 'critical' as SeverityLevel, cwe: 'CWE-78', owasp:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/scanners/vulnerability-scanner.ts",
"line": 57,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/utils/security-scorer.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/utils/security-scorer.ts:81`): 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/utils/security-scorer.ts"
},
"evidence": "nimport { spawn } from 'child_process';\\nconst child = spawn('command', [arg1, arg2]);`, explanation: 'spawn wi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/utils/security-scorer.ts",
"line": 81,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded Stripe secret key in test/example/packaging (examples/test-code.js)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "A hardcoded Stripe secret key (a live-looking credential hardcoded in shipped code) appears in `examples/test-code.js:17`. Verify whether this is a real credential; if so, remove and rotate it.",
"remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
"location": {
"kind": "server",
"name": "examples/test-code.js"
},
"evidence": "Stripe secret key: sk_l…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "stripe-secret",
"file": "examples/test-code.js",
"line": 17
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (examples/test-code.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`examples/test-code.js:23`): 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/test-code.js"
},
"evidence": "nst { exec } = require('child_process'); exec(`ls -la ${userInput}`, (error, stdout) => { console.log(stdout);",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "examples/test-code.js",
"line": 23,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"codeguard-mcp\" 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": "codeguard-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "scanCode",
"tags": [],
"reasons": {}
},
{
"tool": "scanVulnerabilities",
"tags": [],
"reasons": {}
},
{
"tool": "detectSecrets",
"tags": [],
"reasons": {}
},
{
"tool": "suggestSecureFix",
"tags": [],
"reasons": {}
},
{
"tool": "checkCompliance",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "23cb35abe47def8530d5021c7db6f6b92e18fe0e4ca9cc78ca306723b1968d5d",
"stats": {
"tools": 5,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 2,
"info": 1
}
}
}