Cdp Toolkit — 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": "cdp-toolkit",
"source": {
"kind": "package",
"origin": "cdp-toolkit"
},
"server": {
"name": "cdp-toolkit"
}
},
"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-1.9"
},
"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",
"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 (34 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/cli.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cli.js:1659`): 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": "rt { spawn } from \"node:child_process\"; import { mkdir as mkdir6, readFile as readFile4, stat as stat2 } from \"node:fs/p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cli.js",
"line": 1659,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/index.js:1657`): 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/index.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { mkdir as mkdir6, readFile as readFile4, stat as stat2 } from \"node:fs/p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/index.js",
"line": 1657,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/mcp.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/mcp.js:1659`): 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/mcp.js"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { mkdir as mkdir6, readFile as readFile4, stat as stat2 } from \"node:fs/p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/mcp.js",
"line": 1659,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/tools/lighthouse.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/tools/lighthouse.ts: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": "src/tools/lighthouse.ts"
},
"evidence": "rt { spawn } from \"node:child_process\"; import { mkdir, readFile, stat } from \"node:fs/promises\"; import { CdpError } fr",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/tools/lighthouse.ts",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([navigate_page, wait_for, evaluate_script, list_console_messages, list_network_requests, get_network_request, performance_start_trace, mock_request]) co-exist with external-action tools ([upload_file]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow",
"name": "navigate_page → upload_file"
},
"evidence": "untrusted [navigate_page, wait_for, evaluate_script, list_console_messages, list_network_requests, get_network_request, performance_start_trace, mock_request] →",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"navigate_page",
"wait_for",
"evaluate_script",
"list_console_messages",
"list_network_requests",
"get_network_request",
"performance_start_trace",
"mock_request"
],
"sinks": [
"upload_file"
]
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"navigate_page\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"navigate_page\" takes a URL/host parameter \"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": "navigate_page",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"get_network_request\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"get_network_request\" takes a URL/host parameter \"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": "get_network_request",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"navigate_page",
"wait_for",
"evaluate_script",
"list_console_messages",
"list_network_requests",
"get_network_request",
"performance_start_trace",
"mock_request"
],
"sensitiveSource": [],
"externalSink": [
"upload_file"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "list_pages",
"tags": [],
"reasons": {}
},
{
"tool": "new_page",
"tags": [],
"reasons": {}
},
{
"tool": "close_page",
"tags": [],
"reasons": {}
},
{
"tool": "select_page",
"tags": [],
"reasons": {}
},
{
"tool": "navigate_page",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "wait_for",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "evaluate_script",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "take_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "click",
"tags": [],
"reasons": {}
},
{
"tool": "hover",
"tags": [],
"reasons": {}
},
{
"tool": "drag",
"tags": [],
"reasons": {}
},
{
"tool": "fill",
"tags": [],
"reasons": {}
},
{
"tool": "fill_form",
"tags": [],
"reasons": {}
},
{
"tool": "type_text",
"tags": [],
"reasons": {}
},
{
"tool": "press_key",
"tags": [],
"reasons": {}
},
{
"tool": "upload_file",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "take_screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "emulate",
"tags": [],
"reasons": {}
},
{
"tool": "prefers-color-scheme",
"tags": [],
"reasons": {}
},
{
"tool": "resize_page",
"tags": [],
"reasons": {}
},
{
"tool": "handle_dialog",
"tags": [],
"reasons": {}
},
{
"tool": "list_console_messages",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "get_console_message",
"tags": [],
"reasons": {}
},
{
"tool": "list_network_requests",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "get_network_request",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "performance_start_trace",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"get_page\""
]
}
},
{
"tool": "performance_stop_trace",
"tags": [],
"reasons": {}
},
{
"tool": "performance_analyze_insight",
"tags": [],
"reasons": {}
},
{
"tool": "performance_trace",
"tags": [],
"reasons": {}
},
{
"tool": "take_heapsnapshot",
"tags": [],
"reasons": {}
},
{
"tool": "lighthouse_audit",
"tags": [],
"reasons": {}
},
{
"tool": "mock_request",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "list_mocks",
"tags": [],
"reasons": {}
},
{
"tool": "clear_mocks",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "c340ade664a02b8fd2c967c00c4fc86c008671fe81c2780b679f43d9a17a38b7",
"stats": {
"tools": 34,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 3,
"low": 0,
"info": 0
}
}
}