Raw scan report

Obsidian — 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": "@beshkenadze/mcp-obsidian",
    "source": {
      "kind": "package",
      "origin": "@beshkenadze/mcp-obsidian"
    },
    "server": {
      "name": "@beshkenadze/mcp-obsidian"
    }
  },
  "grade": "B",
  "score": {
    "score": 87,
    "threatScore": 94,
    "grade": "B",
    "band": "B",
    "categorySubtotals": {
      "injection": 6.3,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-SRC-009",
        "category": "injection",
        "severity": "medium",
        "confidence": "strong",
        "rawWeight": 9,
        "confidenceMult": 0.7,
        "diminishingFactor": 1,
        "appliedPenalty": 6.3
      },
      {
        "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 create, modify or delete files",
      "reads sensitive or local data",
      "has a read → egress path (a data-exfiltration surface)",
      "can execute shell commands or code"
    ],
    "tags": [
      "sensitive-source",
      "file-write",
      "code-exec"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (23 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 ([obsidian_list_files]) and tools that can send data out ([obsidian_execute_command]) 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": "obsidian_list_files → obsidian_execute_command"
      },
      "evidence": "sources [obsidian_list_files] → sinks [obsidian_execute_command]",
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "references": [],
      "data": {
        "sources": [
          "obsidian_list_files"
        ],
        "sinks": [
          "obsidian_execute_command"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"obsidian_execute_command\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"obsidian_execute_command\" appears to run shell commands or evaluate code (keyword \"execute command\" 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": "obsidian_execute_command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (dist/sse.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/sse.js:436`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/sse.js"
      },
      "evidence": "hrow Error(); Function(` 'use strict' const o = new Proxy({}, { get: () => o, set: ()",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "dist/sse.js",
        "line": 436,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (dist/stdio.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/stdio.js:436`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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/stdio.js"
      },
      "evidence": "hrow Error(); Function(` 'use strict' const o = new Proxy({}, { get: () => o, set: ()",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "dist/stdio.js",
        "line": 436,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/sse.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/sse.js:4283`): 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/sse.js"
      },
      "evidence": "import { spawn } from \"child_process\"; // node_modules/zod/lib/index.mjs var util; (function(util2) { util2.assertEq",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/sse.js",
        "line": 4283,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/stdio.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/stdio.js:4283`): 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/stdio.js"
      },
      "evidence": "import { spawn } from \"child_process\"; // node_modules/zod/lib/index.mjs var util; (function(util2) { util2.assertEq",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/stdio.js",
        "line": 4283,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/bin/run-with-supergateway.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/bin/run-with-supergateway.ts: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": "src/bin/run-with-supergateway.ts"
      },
      "evidence": "import { spawn } from \"child_process\"; import logger from \"../lib/logger\"; // Get the port from environment or use def",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/bin/run-with-supergateway.ts",
        "line": 2,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/cmd/generate-types.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/cmd/generate-types.ts:3`): 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": "src/cmd/generate-types.ts"
      },
      "evidence": "port { execSync } from \"child_process\"; import fs from \"fs\"; import path from \"path\"; // Ensure the output directory ex",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/cmd/generate-types.ts",
        "line": 3,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/servers/mcp-sse-server.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/servers/mcp-sse-server.ts: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": "src/servers/mcp-sse-server.ts"
      },
      "evidence": "import { spawn } from \"child_process\"; import type { McpServerConfig } from \"../lib/common-server\"; import { CommonMcpS",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/servers/mcp-sse-server.ts",
        "line": 1,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-009",
      "title": "Untrusted input concatenated into a command sink (src/cmd/generate-types.ts)",
      "category": "injection",
      "severity": "medium",
      "confidence": "strong",
      "description": "In the server's implementation (`src/cmd/generate-types.ts:33`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "src/cmd/generate-types.ts"
      },
      "evidence": "napi-typescript try { execSync(`bunx openapi-typescript ${inputPath} -o ${outputPath}`, { stdio: \"inherit\", });",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-009",
        "file": "src/cmd/generate-types.ts",
        "line": 33,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-002",
      "title": "Tool \"obsidian_delete_file\" can modify the filesystem",
      "category": "permissions",
      "severity": "medium",
      "confidence": "strong",
      "description": "Tool \"obsidian_delete_file\" can write, overwrite or delete files (keyword \"delete_file\" in tool name). Verify it is scoped to a safe directory.",
      "remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
      "location": {
        "kind": "tool",
        "name": "obsidian_delete_file"
      },
      "data": {
        "tags": [
          "file-write"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"obsidian_delete_file\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"obsidian_delete_file\" 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": "obsidian_delete_file"
      },
      "data": {
        "tags": [
          "file-write"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"obsidian_execute_command\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"obsidian_execute_command\" 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": "obsidian_execute_command"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SUP-012",
      "title": "Package has no license",
      "category": "hygiene",
      "severity": "info",
      "confidence": "strong",
      "description": "\"@beshkenadze/mcp-obsidian\" has no declared license. This is a legal/reuse concern, not a security finding.",
      "location": {
        "kind": "package",
        "name": "@beshkenadze/mcp-obsidian"
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "high",
      "confidence": "strong",
      "untrustedInput": [],
      "sensitiveSource": [
        "obsidian_list_files"
      ],
      "externalSink": [
        "obsidian_execute_command"
      ],
      "selfContained": false,
      "path": [
        "obsidian_list_files",
        "obsidian_execute_command"
      ],
      "pathWired": false,
      "description": "A sensitive-source → external-sink chain exists: obsidian_list_files → obsidian_execute_command."
    }
  ],
  "capabilities": [
    {
      "tool": "obsidian_get_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_get_active_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_update_active_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_append_to_active_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_patch_active_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_delete_active_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_list_files",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"list_files\""
        ]
      }
    },
    {
      "tool": "obsidian_get_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_create_or_update_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_append_to_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_patch_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_delete_file",
      "tags": [
        "file-write"
      ],
      "reasons": {
        "file-write": [
          "keyword \"delete_file\" in tool name"
        ]
      }
    },
    {
      "tool": "obsidian_get_periodic_note",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_update_periodic_note",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_append_to_periodic_note",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_delete_periodic_note",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_patch_periodic_note",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_advanced_search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_open_document",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_list_commands",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "obsidian_execute_command",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"execute command\" in tool name"
        ]
      }
    },
    {
      "tool": "thread-stream",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "fca08b87e03ad80ebb5187be66bfa282b66b9ec2ff1d1723e27dcd358b026ed0",
  "stats": {
    "tools": 23,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 9,
      "medium": 2,
      "low": 2,
      "info": 1
    }
  }
}