Codex — 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": "@anhnguyen0905/codex-mcp",
"source": {
"kind": "package",
"origin": "@anhnguyen0905/codex-mcp"
},
"server": {
"name": "@anhnguyen0905/codex-mcp"
}
},
"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 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 (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-SRC-002",
"title": "Shell/command execution in server code (dist/codexRunner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/codexRunner.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": "dist/codexRunner.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { createIncrementalParser } from './eventParser.js'; export const DEFAULT",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/codexRunner.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/liveView.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/liveView.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": "dist/liveView.js"
},
"evidence": "spawnSync } from 'node:child_process'; import { createWriteStream, lstatSync, mkdirSync, readdirSync, statSync, unlinkS",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/liveView.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/terminal.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/terminal.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": "dist/terminal.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { buildWatcherEnvExports } from './terminalCloser.js'; /** * Known Linux",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/terminal.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/terminalCloser.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/terminalCloser.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": "dist/terminalCloser.js"
},
"evidence": "spawnSync } from 'node:child_process'; /** Grace period before the finished window closes, so the last output stays rea",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/terminalCloser.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/verification.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/verification.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": "dist/verification.js"
},
"evidence": "rt { spawn } from 'node:child_process'; import { z } from 'zod'; /** * Server-side acceptance verification: after a Cod",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/verification.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/workspaceDiff.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/workspaceDiff.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": "dist/workspaceDiff.js"
},
"evidence": "{ execFile } from 'node:child_process'; import { createHash } from 'node:crypto'; import { readFile } from 'node:fs/prom",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/workspaceDiff.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/build-skills-index.mjs)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/build-skills-index.mjs:69`): 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": "scripts/build-skills-index.mjs"
},
"evidence": "{ execFile } from 'node:child_process' import { createHash } from 'node:crypto' import { promises as fs } from 'node:fs'",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/build-skills-index.mjs",
"line": 69,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/context-slice.mjs)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/context-slice.mjs: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": "scripts/context-slice.mjs"
},
"evidence": "ecFileSync } from 'node:child_process' import { randomUUID } from 'node:crypto' import { promises as fs } from 'node:fs'",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/context-slice.mjs",
"line": 1,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/doctor.mjs)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/doctor.mjs: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": "scripts/doctor.mjs"
},
"evidence": "spawnSync } from 'node:child_process' const isWindows = process.platform === 'win32' const MIN_NODE_MAJOR = 20 const",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/doctor.mjs",
"line": 4,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/skill-brief.mjs)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/skill-brief.mjs:7`): 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": "scripts/skill-brief.mjs"
},
"evidence": "ecFileSync } from 'node:child_process' import { existsSync, lstatSync, mkdirSync, readFileSync, realpathSync,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/skill-brief.mjs",
"line": 7,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "codex_execute",
"tags": [],
"reasons": {}
},
{
"tool": "codex_continue",
"tags": [],
"reasons": {}
},
{
"tool": "codex_review",
"tags": [],
"reasons": {}
},
{
"tool": "codex_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "codex_metrics",
"tags": [],
"reasons": {}
},
{
"tool": "codex_batch",
"tags": [],
"reasons": {}
},
{
"tool": "codex_health",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "2092ca1b2c6c833a7568be1f6aa6b2baae4b1b84cd92af6c623ca191751fc99f",
"stats": {
"tools": 7,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 0,
"low": 4,
"info": 0
}
}
}