Raw scan report

Microbit Claude — the complete, unedited output of the deterministic mcptrustchecker engine v1.10.0, 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": "1.10.0",
    "methodologyVersion": "mcptrustchecker-1.9"
  },
  "target": {
    "id": "microbit-claude-mcp",
    "source": {
      "kind": "package",
      "origin": "microbit-claude-mcp"
    },
    "server": {
      "name": "microbit-claude-mcp"
    }
  },
  "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-1.9"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "can send data / act on an external service",
      "can execute shell commands or code"
    ],
    "tags": [
      "code-exec",
      "external-sink"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (16 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 (build/makecode.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`build/makecode.js:20`): 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": "build/makecode.js"
      },
      "evidence": "require(\"path\")); const child_process_1 = require(\"child_process\"); const PXT_BIN = process.env.PXT_BIN ?? \"pxt\"; const",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "build/makecode.js",
        "line": 20,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/index.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/index.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": "dist/index.js"
      },
      "evidence": "require(\"path\")); const child_process_1 = require(\"child_process\"); const help_desk_1 = require(\"./help-desk\"); const ma",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/index.js",
        "line": 9,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/makecode.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/makecode.js:20`): 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/makecode.js"
      },
      "evidence": "require(\"path\")); const child_process_1 = require(\"child_process\"); const PXT_BIN = process.env.PXT_BIN ?? \"pxt\"; const",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/makecode.js",
        "line": 20,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (build/help-desk.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`build/help-desk.js:126`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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": "build/help-desk.js"
      },
      "evidence": "const res = await fetch(\"https://api.anthropic.com/v1/messages\", { method: \"POST\", headers",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "build/help-desk.js",
        "line": 126,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-003",
      "title": "Hardcoded egress to an external endpoint (dist/help-desk.js)",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/help-desk.js:126`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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/help-desk.js"
      },
      "evidence": "const res = await fetch(\"https://api.anthropic.com/v1/messages\", { method: \"POST\", headers",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "data": {
        "rule": "MTC-SRC-003",
        "file": "dist/help-desk.js",
        "line": 126,
        "nonRuntime": false
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "validate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_sources",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_source",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "write_source",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "append_source",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "build",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "makecode_validate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "makecode_read",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "makecode_write",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "makecode_build",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "makecode_init",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "submit_help",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_requests",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_request",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "review_request",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_response",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "1109b762789c45b9a98c1642a0b52b91b5f1c9d41c3f2ab1d950632912e76dd5",
  "stats": {
    "tools": 16,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 3,
      "medium": 2,
      "low": 0,
      "info": 0
    }
  }
}