Argusqa Os — 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": "argusqa-os",
"source": {
"kind": "package",
"origin": "argusqa-os"
},
"server": {
"name": "argusqa-os"
}
},
"grade": "B",
"score": {
"score": 83,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"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": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code",
"untrusted input can reach code execution"
],
"tags": [
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (9 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/cli/chrome-launcher.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/cli/chrome-launcher.js:18`): 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/cli/chrome-launcher.js"
},
"evidence": "FileSync, spawn } from 'child_process'; import fs from 'fs'; import os from 'os'; import path from 'path'; import {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/cli/chrome-launcher.js",
"line": 18,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/orchestration/dispatcher.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/orchestration/dispatcher.js:9`): 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/orchestration/dispatcher.js"
},
"evidence": "from 'child_process'; import { childLogger } from '../utils/logger.js'; i",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/orchestration/dispatcher.js",
"line": 9,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/utils/baseline-manager.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/utils/baseline-manager.js:14`): 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/baseline-manager.js"
},
"evidence": "ort { execSync } from 'child_process'; // Import shared findingKey from flakiness-detector so both modules use // ident",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/utils/baseline-manager.js",
"line": 14,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/utils/mcp-client.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/utils/mcp-client.js: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/utils/mcp-client.js"
},
"evidence": "import { spawn } from 'child_process'; import { childLogger } from './logger.js'; const logger = childLogger('mcp-c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/utils/mcp-client.js",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/utils/root-cause-linker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/utils/root-cause-linker.js:21`): 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/root-cause-linker.js"
},
"evidence": "port { execSync } from 'child_process'; import { INFRA_PATTERNS } from './pr-diff-analyzer.js'; import { childLogger }",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/utils/root-cause-linker.js",
"line": 21,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/utils/screen-recorder.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/utils/screen-recorder.js:28`): 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/screen-recorder.js"
},
"evidence": "import { spawn } from 'child_process'; import fs from 'fs'; import path from 'path'; import http from 'http'; // ──",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/utils/screen-recorder.js",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/utils/security-analyzer.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/utils/security-analyzer.js:21`): 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-analyzer.js"
},
"evidence": "t { execFile } from 'child_process'; import { thresholds } from '../config/targets.js'; import { childLogger } from",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/utils/security-analyzer.js",
"line": 21,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/utils/root-cause-linker.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/utils/root-cause-linker.js:47`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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/root-cause-linker.js"
},
"evidence": "out; try { out = execSync(`git log --name-only --pretty=format:%h%x09%s -n ${Math.max(1, commits | 0)}`, {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/utils/root-cause-linker.js",
"line": 47,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"argus_audit\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"argus_audit\" 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": "argus_audit",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "argus_audit",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"crawl\""
]
}
},
{
"tool": "argus_audit_full",
"tags": [],
"reasons": {}
},
{
"tool": "argus_compare",
"tags": [],
"reasons": {}
},
{
"tool": "argus_last_report",
"tags": [],
"reasons": {}
},
{
"tool": "argus_watch_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "argus_get_context",
"tags": [],
"reasons": {}
},
{
"tool": "argus_visual_diff",
"tags": [],
"reasons": {}
},
{
"tool": "argus_design_audit",
"tags": [],
"reasons": {}
},
{
"tool": "argus_pr_validate",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "fd4938e9590e0a116654b143bf8eeb5d543d7c4078395f0cf03db84fdc36d081",
"stats": {
"tools": 9,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 2,
"low": 0,
"info": 0
}
}
}