Krometrail — 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": "krometrail",
"source": {
"kind": "package",
"origin": "krometrail"
},
"server": {
"name": "krometrail"
}
},
"grade": "A",
"score": {
"score": 94,
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (30 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 (src/adapters/base.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/base.ts: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/adapters/base.ts"
},
"evidence": "ildProcess } from \"node:child_process\"; import type { Readable, Writable } from \"node:stream\"; export interface Prerequ",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/base.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/bun.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/bun.ts: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/adapters/bun.ts"
},
"evidence": "ildProcess } from \"node:child_process\"; import type { Socket } from \"node:net\"; import { resolve as resolvePath } from \"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/bun.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/codelldb.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/codelldb.ts: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/adapters/codelldb.ts"
},
"evidence": "ort { exec } from \"node:child_process\"; import { existsSync } from \"node:fs\"; import { access } from \"node:fs/promises\";",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/codelldb.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/cpp.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/cpp.ts: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/adapters/cpp.ts"
},
"evidence": "ildProcess } from \"node:child_process\"; import { exec, spawn } from \"node:child_process\"; import { tmpdir } from \"node:o",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/cpp.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/csharp.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/csharp.ts: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/adapters/csharp.ts"
},
"evidence": "ildProcess } from \"node:child_process\"; import { exec, spawn } from \"node:child_process\"; import { mkdirSync, writeFileS",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/csharp.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/go.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/go.ts: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/adapters/go.ts"
},
"evidence": "ildProcess } from \"node:child_process\"; import { access } from \"node:fs/promises\"; import type { Socket } from \"node:net",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/go.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/helpers.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/helpers.ts: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/adapters/helpers.ts"
},
"evidence": "ildProcess } from \"node:child_process\"; import { spawn } from \"node:child_process\"; import { createWriteStream, mkdirSyn",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/helpers.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/java.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/java.ts: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/adapters/java.ts"
},
"evidence": "ildProcess } from \"node:child_process\"; import { existsSync } from \"node:fs\"; import type { Socket } from \"node:net\"; im",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/java.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/js-debug-adapter.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/js-debug-adapter.ts: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/adapters/js-debug-adapter.ts"
},
"evidence": "ort { exec } from \"node:child_process\"; import { existsSync } from \"node:fs\"; import { readFile, writeFile } from \"node:",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/js-debug-adapter.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/adapters/kotlin.ts)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/kotlin.ts: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/adapters/kotlin.ts"
},
"evidence": "ildProcess } from \"node:child_process\"; import { exec, spawn } from \"node:child_process\"; import { copyFileSync, existsS",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/adapters/kotlin.ts",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/core/auto-update.ts)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/core/auto-update.ts:107`): 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/core/auto-update.ts"
},
"evidence": "const response = await fetch(\"https://api.github.com/repos/nklisch/krometrail/releases/latest\", { headers: { \"User-A",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/core/auto-update.ts",
"line": 107,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "chrome_start",
"tags": [],
"reasons": {}
},
{
"tool": "chrome_status",
"tags": [],
"reasons": {}
},
{
"tool": "chrome_mark",
"tags": [],
"reasons": {}
},
{
"tool": "chrome_stop",
"tags": [],
"reasons": {}
},
{
"tool": "chrome_refresh",
"tags": [],
"reasons": {}
},
{
"tool": "chrome_run_steps",
"tags": [],
"reasons": {}
},
{
"tool": "session_list",
"tags": [],
"reasons": {}
},
{
"tool": "session_overview",
"tags": [],
"reasons": {}
},
{
"tool": "session_search",
"tags": [],
"reasons": {}
},
{
"tool": "session_inspect",
"tags": [],
"reasons": {}
},
{
"tool": "session_diff",
"tags": [],
"reasons": {}
},
{
"tool": "session_replay_context",
"tags": [],
"reasons": {}
},
{
"tool": "debug_launch",
"tags": [],
"reasons": {}
},
{
"tool": "debug_stop",
"tags": [],
"reasons": {}
},
{
"tool": "debug_status",
"tags": [],
"reasons": {}
},
{
"tool": "debug_continue",
"tags": [],
"reasons": {}
},
{
"tool": "debug_step",
"tags": [],
"reasons": {}
},
{
"tool": "debug_run_to",
"tags": [],
"reasons": {}
},
{
"tool": "debug_set_breakpoints",
"tags": [],
"reasons": {}
},
{
"tool": "debug_set_exception_breakpoints",
"tags": [],
"reasons": {}
},
{
"tool": "debug_list_breakpoints",
"tags": [],
"reasons": {}
},
{
"tool": "debug_evaluate",
"tags": [],
"reasons": {}
},
{
"tool": "debug_variables",
"tags": [],
"reasons": {}
},
{
"tool": "debug_stack_trace",
"tags": [],
"reasons": {}
},
{
"tool": "debug_source",
"tags": [],
"reasons": {}
},
{
"tool": "debug_watch",
"tags": [],
"reasons": {}
},
{
"tool": "debug_action_log",
"tags": [],
"reasons": {}
},
{
"tool": "debug_output",
"tags": [],
"reasons": {}
},
{
"tool": "debug_attach",
"tags": [],
"reasons": {}
},
{
"tool": "debug_threads",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9f7310e46211df165a3ed221dcf6694d00d7b4d1cee5e39b8466f499f9c5ca8c",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 1,
"low": 0,
"info": 0
}
}
}