Circuit Electron — 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": "@snowfort/circuit-electron",
"source": {
"kind": "package",
"origin": "@snowfort/circuit-electron"
},
"server": {
"name": "@snowfort/circuit-electron"
}
},
"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 create, modify or delete files",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"file-write",
"sensitive-source"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (32 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-004",
"title": "Sensitive-source and external-sink co-exist",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "Tools that read sensitive data ([fs_read_file]) and tools that can send data out ([evaluate]) are exposed together. An agent can move private data to the sink.",
"remediation": "Keep secret-reading and egress capabilities on separate, separately-approved servers.",
"location": {
"kind": "flow",
"name": "fs_read_file → evaluate"
},
"evidence": "sources [fs_read_file] → sinks [evaluate]",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"sources": [
"fs_read_file"
],
"sinks": [
"evaluate"
]
}
},
{
"ruleId": "MTC-CAP-001",
"title": "Tool \"evaluate\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"evaluate\" appears to run shell commands or evaluate code (parameter \"script\"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "evaluate"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/cjs/electron-driver.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/cjs/electron-driver.js:41`): 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/cjs/electron-driver.js"
},
"evidence": "= require(\"fs\"); const child_process_1 = require(\"child_process\"); const util_1 = require(\"util\"); const path = __impor",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/cjs/electron-driver.js",
"line": 41,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/esm/electron-driver.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/esm/electron-driver.js:5`): 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/esm/electron-driver.js"
},
"evidence": "t { exec, spawn } from \"child_process\"; import { promisify } from \"util\"; import * as path from \"path\"; import * as os f",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/esm/electron-driver.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"fs_write_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"fs_write_file\" can write, overwrite or delete files (keyword \"write_file\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "fs_write_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-006",
"title": "Unconstrained command parameter \"script\" on \"evaluate\"",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"evaluate\" takes a command-shaped parameter \"script\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
"remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
"location": {
"kind": "tool",
"name": "evaluate",
"field": "inputSchema.properties.script"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"param": "script"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/cjs/electron-driver.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/cjs/electron-driver.js:237`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/cjs/electron-driver.js"
},
"evidence": ".then(s => __importStar(require(s))); debugInfo.push(`[PLAYWRIGHT-DEBUG] ✓ ESM dynamic import succeeded`",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/cjs/electron-driver.js",
"line": 237,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (dist/esm/electron-driver.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`dist/esm/electron-driver.js:201`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/esm/electron-driver.js"
},
"evidence": "ojectPlaywright = await import(projectPlaywrightPath); debugInfo.push(`[PLAYWRIGHT-DEBUG] ✓ ESM dynamic",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "dist/esm/electron-driver.js",
"line": 201,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"evaluate\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"evaluate\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "evaluate"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"fs_write_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"fs_write_file\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "fs_write_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"filePath\" on \"fs_write_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"fs_write_file\" takes a path parameter \"filePath\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "fs_write_file",
"field": "inputSchema.properties.filePath"
},
"data": {
"param": "filePath"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"filePath\" on \"fs_read_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"fs_read_file\" takes a path parameter \"filePath\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "fs_read_file",
"field": "inputSchema.properties.filePath"
},
"data": {
"param": "filePath"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "high",
"confidence": "strong",
"untrustedInput": [],
"sensitiveSource": [
"fs_read_file"
],
"externalSink": [
"evaluate"
],
"selfContained": false,
"path": [
"fs_read_file",
"evaluate"
],
"pathWired": false,
"description": "A sensitive-source → external-sink chain exists: fs_read_file → evaluate."
}
],
"capabilities": [
{
"tool": "app_launch",
"tags": [],
"reasons": {}
},
{
"tool": "click",
"tags": [],
"reasons": {}
},
{
"tool": "type",
"tags": [],
"reasons": {}
},
{
"tool": "screenshot",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"parameter \"script\""
]
}
},
{
"tool": "wait_for_selector",
"tags": [],
"reasons": {}
},
{
"tool": "ipc_invoke",
"tags": [],
"reasons": {}
},
{
"tool": "get_windows",
"tags": [],
"reasons": {}
},
{
"tool": "fs_write_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"write_file\" in tool name"
]
}
},
{
"tool": "fs_read_file",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "close",
"tags": [],
"reasons": {}
},
{
"tool": "keyboard_press",
"tags": [],
"reasons": {}
},
{
"tool": "click_by_text",
"tags": [],
"reasons": {}
},
{
"tool": "add_locator_handler",
"tags": [],
"reasons": {}
},
{
"tool": "click_by_role",
"tags": [],
"reasons": {}
},
{
"tool": "click_nth",
"tags": [],
"reasons": {}
},
{
"tool": "keyboard_type",
"tags": [],
"reasons": {}
},
{
"tool": "wait_for_load_state",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "hover",
"tags": [],
"reasons": {}
},
{
"tool": "drag",
"tags": [],
"reasons": {}
},
{
"tool": "key",
"tags": [],
"reasons": {}
},
{
"tool": "select",
"tags": [],
"reasons": {}
},
{
"tool": "upload",
"tags": [],
"reasons": {}
},
{
"tool": "back",
"tags": [],
"reasons": {}
},
{
"tool": "forward",
"tags": [],
"reasons": {}
},
{
"tool": "refresh",
"tags": [],
"reasons": {}
},
{
"tool": "content",
"tags": [],
"reasons": {}
},
{
"tool": "text_content",
"tags": [],
"reasons": {}
},
{
"tool": "smart_click",
"tags": [],
"reasons": {}
},
{
"tool": "browser_network_requests",
"tags": [],
"reasons": {}
},
{
"tool": "browser_console_messages",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "79f39665ade40315c04c867dc905023d6aac28a965f134e925af08432ed8c964",
"stats": {
"tools": 32,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 4,
"low": 4,
"info": 0
}
}
}