Noyrax — 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": "@noyrax/mcp-server",
"source": {
"kind": "package",
"origin": "@noyrax/mcp-server"
},
"server": {
"name": "@noyrax/mcp-server"
}
},
"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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"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 (46 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 (out/plugins/database-plugin-adapter.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`out/plugins/database-plugin-adapter.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": "out/plugins/database-plugin-adapter.js"
},
"evidence": "port { execSync } from 'child_process'; /** * Adapter for 5D Database Plugin APIs. * Provides access to database funct",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "out/plugins/database-plugin-adapter.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (out/plugins/documentation-plugin-adapter.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`out/plugins/documentation-plugin-adapter.js:3`): 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": "out/plugins/documentation-plugin-adapter.js"
},
"evidence": "exec, execSync } from 'child_process'; import { promisify } from 'util'; import { createRequire } from 'module'; import",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "out/plugins/documentation-plugin-adapter.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (out/tools/database-tools.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`out/tools/database-tools.js: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": "out/tools/database-tools.js"
},
"evidence": "; import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); /** * Data",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "out/tools/database-tools.js",
"line": 4,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (out/tools/drift-tools.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`out/tools/drift-tools.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": "out/tools/drift-tools.js"
},
"evidence": "ort { exec } from 'node:child_process'; import { promisify } from 'node:util'; import * as fs from 'node:fs/promises'; i",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "out/tools/drift-tools.js",
"line": 8,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (out/tools/path-alias-healing.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`out/tools/path-alias-healing.js:142`): 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": "out/tools/path-alias-healing.js"
},
"evidence": "exec } = await import('child_process'); const { promisify } = await import('util'); con",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "out/tools/path-alias-healing.js",
"line": 142,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "query_modules",
"tags": [],
"reasons": {}
},
{
"tool": "query_symbols",
"tags": [],
"reasons": {}
},
{
"tool": "query_dependencies",
"tags": [],
"reasons": {}
},
{
"tool": "query_adrs",
"tags": [],
"reasons": {}
},
{
"tool": "query_changes",
"tags": [],
"reasons": {}
},
{
"tool": "cross_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "semantic_discovery",
"tags": [],
"reasons": {}
},
{
"tool": "system_explanation",
"tags": [],
"reasons": {}
},
{
"tool": "learning_path",
"tags": [],
"reasons": {}
},
{
"tool": "bootstrap",
"tags": [],
"reasons": {}
},
{
"tool": "gap_analysis",
"tags": [],
"reasons": {}
},
{
"tool": "architecture_mining",
"tags": [],
"reasons": {}
},
{
"tool": "generate_documentation",
"tags": [],
"reasons": {}
},
{
"tool": "check_docs_status",
"tags": [],
"reasons": {}
},
{
"tool": "adr_generator",
"tags": [],
"reasons": {}
},
{
"tool": "generate_adr",
"tags": [],
"reasons": {}
},
{
"tool": "vector_backend_status",
"tags": [],
"reasons": {}
},
{
"tool": "vector_backend_healthcheck",
"tags": [],
"reasons": {}
},
{
"tool": "source_access_contract",
"tags": [],
"reasons": {}
},
{
"tool": "source_snippet",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "validation_runDriftCheck",
"tags": [],
"reasons": {}
},
{
"tool": "validation_analyzeImpact",
"tags": [],
"reasons": {}
},
{
"tool": "validation_verifyAdrs",
"tags": [],
"reasons": {}
},
{
"tool": "validation_runScan",
"tags": [],
"reasons": {}
},
{
"tool": "validation_runValidate",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_full_cycle",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_generate_and_ingest",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_check_status",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_ensure_ready",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_onboard",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_boundary_report",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_path_alias_healing",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_ingest",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_autonomous_feature",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_autonomous_refactoring",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_autonomous_documentation",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_co_partner_plan",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_co_partner_feedback",
"tags": [],
"reasons": {}
},
{
"tool": "workflow_co_partner_rollback",
"tags": [],
"reasons": {}
},
{
"tool": "system_contract",
"tags": [],
"reasons": {}
},
{
"tool": "tools_manifest",
"tags": [],
"reasons": {}
},
{
"tool": "onboarding_report",
"tags": [],
"reasons": {}
},
{
"tool": "export_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "snapshot_get",
"tags": [],
"reasons": {}
},
{
"tool": "import_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "explain_tools",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "3a609e7291262edb65f3dc813d2091babfe01e5298d79d03a49c7f31550db657",
"stats": {
"tools": 46,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 0,
"info": 0
}
}
}