Raw scan report

Winreach — 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.

← Back to the scan page
{
  "tool": {
    "name": "mcptrustchecker",
    "version": "1.9.0",
    "methodologyVersion": "mcptrustchecker-1.9"
  },
  "target": {
    "id": "winreach-mcp",
    "source": {
      "kind": "package",
      "origin": "winreach-mcp"
    },
    "server": {
      "name": "winreach-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": [
      "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 (9 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 \"powershell_execute\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"powershell_execute\" appears to run shell commands or evaluate code (keyword \"powershell\" 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": "powershell_execute"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"powershell_open_session\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"powershell_open_session\" appears to run shell commands or evaluate code (keyword \"powershell\" 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": "powershell_open_session"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"powershell_send\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"powershell_send\" appears to run shell commands or evaluate code (keyword \"powershell\" 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": "powershell_send"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"powershell_close_session\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"powershell_close_session\" appears to run shell commands or evaluate code (keyword \"powershell\" 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": "powershell_close_session"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"powershell_list_sessions\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"powershell_list_sessions\" appears to run shell commands or evaluate code (keyword \"powershell\" 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": "powershell_list_sessions"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/src/powershell/session.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/src/powershell/session.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/src/powershell/session.js"
      },
      "evidence": "rt { spawn } from \"node:child_process\"; import { randomUUID } from \"node:crypto\"; import { createOutputBuffer } from \"./",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/src/powershell/session.js",
        "line": 1,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/src/powershell/shell.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/src/powershell/shell.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/src/powershell/shell.js"
      },
      "evidence": "rt { spawn } from \"node:child_process\"; import { randomUUID } from \"node:crypto\"; import { createOutputBuffer } from \"./",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/src/powershell/shell.js",
        "line": 1,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/src/tunnel.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/src/tunnel.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/src/tunnel.js"
      },
      "evidence": "spawnSync } from \"node:child_process\"; import { chmodSync, createWriteStream, existsSync, mkdirSync } from \"node:fs\"; i",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/src/tunnel.js",
        "line": 1,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-FLOW-005",
      "title": "Untrusted input can drive an external action",
      "category": "exfiltration",
      "severity": "medium",
      "confidence": "strong",
      "description": "Untrusted-input tools ([file_download]) co-exist with external-action tools ([powershell_execute, powershell_open_session, powershell_send, powershell_close_session, powershell_list_sessions]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
      "remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
      "location": {
        "kind": "flow",
        "name": "file_download → powershell_execute"
      },
      "evidence": "untrusted [file_download] → sinks [powershell_execute, powershell_open_session, powershell_send, powershell_close_session, powershell_list_sessions]",
      "owasp": "LLM06:2025 Excessive Agency",
      "references": [],
      "data": {
        "untrusted": [
          "file_download"
        ],
        "sinks": [
          "powershell_execute",
          "powershell_open_session",
          "powershell_send",
          "powershell_close_session",
          "powershell_list_sessions"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"powershell_execute\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"powershell_execute\" 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": "powershell_execute"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"powershell_open_session\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"powershell_open_session\" 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": "powershell_open_session"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"powershell_send\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"powershell_send\" 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": "powershell_send"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"powershell_close_session\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"powershell_close_session\" 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": "powershell_close_session"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"powershell_list_sessions\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"powershell_list_sessions\" 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": "powershell_list_sessions"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "medium",
      "confidence": "strong",
      "untrustedInput": [
        "file_download"
      ],
      "sensitiveSource": [],
      "externalSink": [
        "powershell_execute",
        "powershell_open_session",
        "powershell_send",
        "powershell_close_session",
        "powershell_list_sessions"
      ],
      "selfContained": false,
      "description": "Untrusted input can drive an external action even though no sensitive source is exposed."
    }
  ],
  "capabilities": [
    {
      "tool": "computer_use",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "file_upload",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "file_download",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"download\""
        ]
      }
    },
    {
      "tool": "powershell_execute",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"powershell\" in tool name"
        ]
      }
    },
    {
      "tool": "powershell_open_session",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"powershell\" in tool name"
        ]
      }
    },
    {
      "tool": "powershell_send",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"powershell\" in tool name"
        ]
      }
    },
    {
      "tool": "powershell_close_session",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"powershell\" in tool name"
        ]
      }
    },
    {
      "tool": "powershell_list_sessions",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"powershell\" in tool name"
        ]
      }
    },
    {
      "tool": "take_screenshot",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "d177e2f06c4b512f2c83a0486e475b35002f99bd2ea01927d8756cd235d6eb26",
  "stats": {
    "tools": 9,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 8,
      "medium": 1,
      "low": 5,
      "info": 0
    }
  }
}