Raw scan report

Nitpick — 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": "@buyhatke-dev/nitpick-mcp",
    "source": {
      "kind": "package",
      "origin": "@buyhatke-dev/nitpick-mcp"
    },
    "server": {
      "name": "@buyhatke-dev/nitpick-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-1.13"
  },
  "capability": {
    "level": "high",
    "reasons": [
      "can send data / act on an external service",
      "reads sensitive or local data",
      "has a read → egress path (a data-exfiltration surface)",
      "can execute shell commands or code"
    ],
    "tags": [
      "code-exec",
      "external-sink",
      "sensitive-source"
    ]
  },
  "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-FLOW-004",
      "title": "Sensitive-source and external-sink co-exist",
      "category": "exfiltration",
      "severity": "high",
      "confidence": "strong",
      "description": "Tools that read sensitive data ([export_data]) and tools that can send data out ([evaluate, upload_file]) are exposed together. An agent can move private data to the sink.",
      "remediation": "Keep secret-reading and egress capabilities on separate, separately-approved servers.",
      "location": {
        "kind": "flow",
        "name": "export_data → evaluate"
      },
      "evidence": "sources [export_data] → sinks [evaluate, upload_file]",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "references": [],
      "data": {
        "sources": [
          "export_data"
        ],
        "sinks": [
          "evaluate",
          "upload_file"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"evaluate\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"evaluate\" appears to run shell commands or evaluate code (parameter \"script\"). 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": "evaluate"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/report.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/report.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/report.js"
      },
      "evidence": "ecFileSync } from \"node:child_process\"; const SEV_COLOR = { high: \"#b91c1c\", medium: \"#c2410c\", low: \"#15803d\" }; const",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/report.js",
        "line": 2,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/util/sh.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/util/sh.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/util/sh.js"
      },
      "evidence": "{ execFile } from \"node:child_process\"; const MAX_BUFFER = 64 * 1024 * 1024; // 64MB — screenshots/hierarchy dumps are l",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/util/sh.js",
        "line": 1,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-006",
      "title": "Unconstrained command parameter \"script\" on \"evaluate\"",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "Tool \"evaluate\" takes a command-shaped parameter \"script\" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.",
      "remediation": "Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.",
      "location": {
        "kind": "tool",
        "name": "evaluate",
        "field": "inputSchema.properties.script"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "param": "script"
      }
    },
    {
      "ruleId": "MTC-SRC-005",
      "title": "Dynamic module load from a non-literal (dist/doctor.js)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "In the server's implementation (`dist/doctor.js:28`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/doctor.js"
      },
      "evidence": "st { chromium } = await import(spec); const p = chromium.executablePath(); return !!p && existsSync(p);",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-005",
        "file": "dist/doctor.js",
        "line": 28,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-005",
      "title": "Dynamic module load from a non-literal (dist/drivers/playwright.js)",
      "category": "permissions",
      "severity": "medium",
      "confidence": "heuristic",
      "description": "In the server's implementation (`dist/drivers/playwright.js:42`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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/drivers/playwright.js"
      },
      "evidence": "({ chromium } = await import(spec)); } catch { throw new Error(\"Playwright is not installe",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-005",
        "file": "dist/drivers/playwright.js",
        "line": 42,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"evaluate\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"evaluate\" 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": "evaluate"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-008",
      "title": "Unconstrained path parameter \"filename\" on \"export_data\"",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"export_data\" takes a path parameter \"filename\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
      "remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
      "location": {
        "kind": "tool",
        "name": "export_data",
        "field": "inputSchema.properties.filename"
      },
      "data": {
        "param": "filename"
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "high",
      "confidence": "strong",
      "untrustedInput": [],
      "sensitiveSource": [
        "export_data"
      ],
      "externalSink": [
        "evaluate",
        "upload_file"
      ],
      "selfContained": false,
      "path": [
        "export_data",
        "evaluate"
      ],
      "pathWired": false,
      "description": "A sensitive-source → external-sink chain exists: export_data → evaluate."
    }
  ],
  "capabilities": [
    {
      "tool": "start_session",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "doctor",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "capture",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "tap",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "long_press",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "scroll",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "input",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "press",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "run_flow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "observe",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "evaluate",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "parameter \"script\""
        ]
      }
    },
    {
      "tool": "wait",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "export_report",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_findings",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "login",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "save_auth",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_brief",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_map",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "save_flow",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "record_finding",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "navigate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "open_tab",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_tabs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "switch_tab",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "close_tab",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "current_page",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "hover",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "focus",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "select_option",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "set_checked",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "drag",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "upload_file",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"upload_file\""
        ]
      }
    },
    {
      "tool": "scroll_to",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "inspect_ui",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "extract_ui",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "save_ui_state",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "compare_ui_state",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "audit_ui",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "export_data",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"export_data\""
        ]
      }
    }
  ],
  "surfaceDigest": "486a4d85e6fb95e126d0b06f68594bcf88cf80c1b66f5dc3232cace0975ec53a",
  "stats": {
    "tools": 39,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 4,
      "medium": 3,
      "low": 2,
      "info": 0
    }
  }
}