Manager Protocol — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "@trentapps/manager-protocol",
"source": {
"kind": "package",
"origin": "@trentapps/manager-protocol"
},
"server": {
"name": "@trentapps/manager-protocol"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "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-1.9"
},
"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 (39 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-CAP-001",
"title": "Tool \"css_eval\" exposes command/code execution",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "Tool \"css_eval\" appears to run shell commands or evaluate code (keyword \"eval\" in tool name). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.",
"remediation": "Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.",
"location": {
"kind": "tool",
"name": "css_eval"
},
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engine/GitHubApprovalManager.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/GitHubApprovalManager.js: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": "dist/engine/GitHubApprovalManager.js"
},
"evidence": "/ import { exec } from 'child_process'; import { promisify } from 'util'; import { writeFileSync, unlinkSync } from 'fs'",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engine/GitHubApprovalManager.js",
"line": 7,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/engine/GitHubClient.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/engine/GitHubClient.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": "dist/engine/GitHubClient.js"
},
"evidence": "; import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); /** * GitH",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/engine/GitHubClient.js",
"line": 15,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/server.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/server.js:6`): 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/server.js"
},
"evidence": "/ import { exec } from 'child_process'; import { promisify } from 'util'; import { Server } from '@modelcontextprotocol/",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/server.js",
"line": 6,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/supervisor/ProjectTracker.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/supervisor/ProjectTracker.js:10`): 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/supervisor/ProjectTracker.js"
},
"evidence": "/ import { exec } from 'child_process'; import { promisify } from 'util'; import path from 'path'; import fs from 'fs';",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/supervisor/ProjectTracker.js",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"css_eval\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"css_eval\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "css_eval"
},
"data": {
"tags": [
"code-exec"
]
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"@trentapps/manager-protocol\" 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": "@trentapps/manager-protocol"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "modify_database",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate_action",
"tags": [],
"reasons": {}
},
{
"tool": "apply_business_rules",
"tags": [],
"reasons": {}
},
{
"tool": "require_human_approval",
"tags": [],
"reasons": {}
},
{
"tool": "log_event",
"tags": [],
"reasons": {}
},
{
"tool": "check_approval_status",
"tags": [],
"reasons": {}
},
{
"tool": "list_pending_approvals",
"tags": [],
"reasons": {}
},
{
"tool": "approve_request",
"tags": [],
"reasons": {}
},
{
"tool": "deny_request",
"tags": [],
"reasons": {}
},
{
"tool": "list_rules",
"tags": [],
"reasons": {}
},
{
"tool": "list_project_profiles",
"tags": [],
"reasons": {}
},
{
"tool": "discover_relevant_rules",
"tags": [],
"reasons": {}
},
{
"tool": "add_rule",
"tags": [],
"reasons": {}
},
{
"tool": "remove_rule",
"tags": [],
"reasons": {}
},
{
"tool": "load_preset",
"tags": [],
"reasons": {}
},
{
"tool": "get_audit_events",
"tags": [],
"reasons": {}
},
{
"tool": "get_audit_stats",
"tags": [],
"reasons": {}
},
{
"tool": "get_approval_stats",
"tags": [],
"reasons": {}
},
{
"tool": "export_audit_log",
"tags": [],
"reasons": {}
},
{
"tool": "get_config",
"tags": [],
"reasons": {}
},
{
"tool": "update_config",
"tags": [],
"reasons": {}
},
{
"tool": "check_rate_limit",
"tags": [],
"reasons": {}
},
{
"tool": "add_rate_limit",
"tags": [],
"reasons": {}
},
{
"tool": "calculate_risk_score",
"tags": [],
"reasons": {}
},
{
"tool": "health_check",
"tags": [],
"reasons": {}
},
{
"tool": "css_eval",
"tags": [
"code-exec"
],
"reasons": {
"code-exec": [
"keyword \"eval\" in tool name"
]
}
},
{
"tool": "analyze_css_cleanup",
"tags": [],
"reasons": {}
},
{
"tool": "suggest_css_variables",
"tags": [],
"reasons": {}
},
{
"tool": "register_session",
"tags": [],
"reasons": {}
},
{
"tool": "complete_session",
"tags": [],
"reasons": {}
},
{
"tool": "create_github_issue",
"tags": [],
"reasons": {}
},
{
"tool": "list_github_issues",
"tags": [],
"reasons": {}
},
{
"tool": "update_github_issue",
"tags": [],
"reasons": {}
},
{
"tool": "close_github_issue",
"tags": [],
"reasons": {}
},
{
"tool": "All Governance Rules",
"tags": [],
"reasons": {}
},
{
"tool": "Rule Presets",
"tags": [],
"reasons": {}
},
{
"tool": "Supervisor Configuration",
"tags": [],
"reasons": {}
},
{
"tool": "Supervisor Statistics",
"tags": [],
"reasons": {}
},
{
"tool": "CLAUDE.md Instructions",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "b40b158e7fcfa43aa3e4314a1ade45d873e2c6949a54f0361bb0e9c84e2486d1",
"stats": {
"tools": 39,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 0,
"low": 1,
"info": 1
}
}
}