Raw scan report

Claude Code Toolkit — 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.

← Back to the scan page
{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.13.0",
    "methodologyVersion": "mcptrustchecker-1.13"
  },
  "target": {
    "id": "@asifkibria/claude-code-toolkit",
    "source": {
      "kind": "package",
      "origin": "@asifkibria/claude-code-toolkit"
    },
    "server": {
      "name": "@asifkibria/claude-code-toolkit"
    }
  },
  "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": [
      "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 (40 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/cli.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/cli.js:629`): 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/cli.js"
      },
      "evidence": "spawn } = await import(\"child_process\"); const args = process.argv.slice(2).filter(a => a !== \"--daemon\").concat",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/cli.js",
        "line": 629,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/lib/dashboard.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/lib/dashboard.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/lib/dashboard.js"
      },
      "evidence": "port { execFile } from \"child_process\"; import { generateDashboardHTML } from \"./dashboard-ui.js\"; import { analyzeClaud",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/lib/dashboard.js",
        "line": 5,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/lib/git.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/lib/git.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": "dist/lib/git.js"
      },
      "evidence": "{ execFileSync } from \"child_process\"; import { listSessions } from \"./session-recovery.js\"; const CLAUDE_DIR = path.jo",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/lib/git.js",
        "line": 4,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/lib/mcp-validator.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/lib/mcp-validator.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": "dist/lib/mcp-validator.js"
      },
      "evidence": "FileSync, spawn } from \"child_process\"; const CLAUDE_DIR = path.join(os.homedir(), \".claude\"); function commandExists(co",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/lib/mcp-validator.js",
        "line": 4,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/lib/utils.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/lib/utils.js:35`): 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/lib/utils.js"
      },
      "evidence": "{ execFile } = require(\"child_process\"); const platform = process.platform; if (platform === \"darwin\") {",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/lib/utils.js",
        "line": 35,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (dist/__tests__/git.test.js)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/__tests__/git.test.js:30`): 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.test.js"
      },
      "evidence": "ecFileSync } = require(\"child_process\"); const repoDir = path.join(TEST_DIR, \"my-repo\"); fs.mkdi",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/__tests__/git.test.js",
        "line": 30,
        "nonRuntime": true
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "scan_image_issues",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "fix_image_issues",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_conversation_stats",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_backups",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "restore_backup",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "cleanup_backups",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "health_check",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "export_conversation",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "estimate_context_size",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "usage_analytics",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "find_duplicates",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "archive_conversations",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "run_maintenance",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "clean_claude_directory",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "validate_mcp_config",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_sessions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "recover_session",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "usage_report",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "run_doctor",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_hooks",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "scaffold_hook",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_profiles",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "switch_profile",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "save_profile",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "unstick_session",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "security_scan",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "audit_session",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "enforce_retention",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "inventory_traces",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "clean_traces",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "wipe_traces",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "generate_trace_guard",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "start_dashboard",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_conversations",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "estimate_cost",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "scan_pii",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "mcp_performance",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "git_integration",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "check_alerts",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "check_quotas",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "219c4f1f595ba767b39edc2a5e7429903814454b7925066898f15cf017b8b6cf",
  "stats": {
    "tools": 40,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 5,
      "medium": 0,
      "low": 1,
      "info": 0
    }
  }
}