Seu Claude — 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": "seu-claude",
"source": {
"kind": "package",
"origin": "seu-claude"
},
"server": {
"name": "seu-claude"
}
},
"grade": "B",
"score": {
"score": 80,
"threatScore": 88,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 12.29,
"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": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.25,
"appliedPenalty": 1.58
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
},
{
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"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 (dist/adapters/sandbox/DockerSandbox.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/adapters/sandbox/DockerSandbox.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/adapters/sandbox/DockerSandbox.js"
},
"evidence": "spawn, execSync } from 'child_process'; import { randomUUID } from 'crypto'; /** * DockerSandbox - Secure sandbox using",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/adapters/sandbox/DockerSandbox.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/adapters/sandbox/ESLintValidator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/adapters/sandbox/ESLintValidator.js:2`): 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/adapters/sandbox/ESLintValidator.js"
},
"evidence": "; import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); /** * ESLi",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/adapters/sandbox/ESLintValidator.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/adapters/sandbox/ProcessSandbox.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/adapters/sandbox/ProcessSandbox.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/adapters/sandbox/ProcessSandbox.js"
},
"evidence": "import { spawn } from 'child_process'; import { randomUUID } from 'crypto'; /** * ProcessSandbox - Lightweight sandbox",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/adapters/sandbox/ProcessSandbox.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/adapters/sandbox/ResourceLimiter.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/adapters/sandbox/ResourceLimiter.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/adapters/sandbox/ResourceLimiter.js"
},
"evidence": "port { execSync } from 'child_process'; /** * Parse memory string to bytes */ function parseMemory(memory) { const",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/adapters/sandbox/ResourceLimiter.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/adapters/sandbox/TypeScriptValidator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/adapters/sandbox/TypeScriptValidator.js:2`): 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/adapters/sandbox/TypeScriptValidator.js"
},
"evidence": "; import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); /** * Type",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/adapters/sandbox/TypeScriptValidator.js",
"line": 2,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/adapters/sandbox/DockerSandbox.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/adapters/sandbox/DockerSandbox.js:43`): 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": "dist/adapters/sandbox/DockerSandbox.js"
},
"evidence": "try { execSync(`docker pull ${this.options.image}`, { stdio: 'pipe', t",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/adapters/sandbox/DockerSandbox.js",
"line": 43,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/adapters/sandbox/ResourceLimiter.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/adapters/sandbox/ResourceLimiter.js:249`): 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": "dist/adapters/sandbox/ResourceLimiter.js"
},
"evidence": "const output = execSync(`ps -p ${pid} -o rss=`, { encoding: 'utf-8', stdio: 'pipe' }); const rs",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/adapters/sandbox/ResourceLimiter.js",
"line": 249,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/indexer/git-tracker.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/indexer/git-tracker.js:35`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/indexer/git-tracker.js"
},
"evidence": "= await Promise.resolve(execSync(`git log --since=\"${sinceStr}\" --name-only --pretty=format: | sort -u | grep -v '^$'`,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/indexer/git-tracker.js",
"line": 35,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/adapters/sandbox/DockerSandbox.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/adapters/sandbox/DockerSandbox.ts:57`): 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/adapters/sandbox/DockerSandbox.ts"
},
"evidence": "exists) try { execSync(`docker pull ${this.options.image}`, { stdio: 'pipe', timeout: 120000,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/adapters/sandbox/DockerSandbox.ts",
"line": 57,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (src/indexer/git-tracker.ts)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/indexer/git-tracker.ts:71`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "src/indexer/git-tracker.ts"
},
"evidence": "romise.resolve( execSync( `git log --since=\"${sinceStr}\" --name-only --pretty=format: | sort -u | grep",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "src/indexer/git-tracker.ts",
"line": 71,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (benchmarks/performance.ts)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`benchmarks/performance.ts:12`): 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": "benchmarks/performance.ts"
},
"evidence": "n, ChildProcess } from 'child_process'; import { writeFileSync, mkdirSync, existsSync, rmSync } from 'fs'; import { join",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "benchmarks/performance.ts",
"line": 12,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/__tests__/crawler.test.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/crawler.test.js:269`): 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/__tests__/crawler.test.js"
},
"evidence": "cSync } = await import('child_process'); execSync('git init', { cwd: gitDir, stdio: 'ignore' });",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/__tests__/crawler.test.js",
"line": 269,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/__tests__/git-tracker.test.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/git-tracker.test.js:8`): 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/__tests__/git-tracker.test.js"
},
"evidence": "port { execSync } from 'child_process'; describe('GitTracker', () => { let gitDir; let nonGitDir; let gitTra",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/__tests__/git-tracker.test.js",
"line": 8,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/adapters/sandbox/DockerSandbox.test.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/adapters/sandbox/DockerSandbox.test.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/adapters/sandbox/DockerSandbox.test.js"
},
"evidence": "port { execSync } from 'child_process'; import { DockerSandbox } from './DockerSandbox.js'; // Check Docker availability",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/adapters/sandbox/DockerSandbox.test.js",
"line": 5,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (dist/adapters/sandbox/ResourceLimiter.test.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/adapters/sandbox/ResourceLimiter.test.js:158`): 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/adapters/sandbox/ResourceLimiter.test.js"
},
"evidence": "spawn } = await import('child_process'); const proc = spawn('node', [scriptPath]); // Wait for p",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/adapters/sandbox/ResourceLimiter.test.js",
"line": 158,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"seu-claude\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "seu-claude"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"seu-claude\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "seu-claude"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "index_codebase",
"tags": [],
"reasons": {}
},
{
"tool": "search_codebase",
"tags": [],
"reasons": {}
},
{
"tool": "read_semantic_context",
"tags": [],
"reasons": {}
},
{
"tool": "search_xrefs",
"tags": [],
"reasons": {}
},
{
"tool": "get_stats",
"tags": [],
"reasons": {}
},
{
"tool": "get_token_analytics",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_token\""
]
}
},
{
"tool": "get_memory_profile",
"tags": [],
"reasons": {}
},
{
"tool": "get_query_analytics",
"tags": [],
"reasons": {}
},
{
"tool": "search_symbols",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9870f1b828a192a6b1e01437580f343967f7e4317eedced9db1705e373e95746",
"stats": {
"tools": 9,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 5,
"low": 5,
"info": 2
}
}
}