Raw scan report

Inkstone — 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": "inkstone-mcp",
    "source": {
      "kind": "package",
      "origin": "inkstone-mcp"
    },
    "server": {
      "name": "inkstone-mcp"
    }
  },
  "grade": "A",
  "score": {
    "score": 91,
    "threatScore": 99,
    "grade": "A",
    "band": "A",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 1.2,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "threat",
        "ruleId": "MTC-SUP-010",
        "category": "supply-chain",
        "severity": "low",
        "confidence": "heuristic",
        "rawWeight": 3,
        "confidenceMult": 0.4,
        "diminishingFactor": 1,
        "appliedPenalty": 1.2
      },
      {
        "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": "none",
        "label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
        "appliedPenalty": 2
      },
      {
        "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 (29 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/llm/client.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/llm/client.js:7`): 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/llm/client.js"
      },
      "evidence": "{ execSync } from \"node:child_process\"; import { OLLAMA_URL, OLLAMA_CHAT_MODEL, OPENROUTER_API_KEY, OPENROUTER_URL, OPEN",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/llm/client.js",
        "line": 7,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/nightly/pipeline.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/nightly/pipeline.js:8`): 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/nightly/pipeline.js"
      },
      "evidence": ", execSync } from \"node:child_process\"; import { existsSync, readFileSync, writeFileSync, mkdirSync } from \"node:fs\"; im",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/nightly/pipeline.js",
        "line": 8,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (dist/nlm/client.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`dist/nlm/client.js:7`): 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/nlm/client.js"
      },
      "evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; const execFileAsync = promisify(execFile)",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/nlm/client.js",
        "line": 7,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/llm/client.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/llm/client.ts:8`): 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/llm/client.ts"
      },
      "evidence": "{ execSync } from \"node:child_process\"; import { OLLAMA_URL, OLLAMA_CHAT_MODEL, OPENROUTER_API_KEY, OPENROUTER_URL,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/llm/client.ts",
        "line": 8,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/nightly/pipeline.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/nightly/pipeline.ts: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": "src/nightly/pipeline.ts"
      },
      "evidence": ", execSync } from \"node:child_process\"; import { existsSync, readFileSync, writeFileSync, mkdirSync } from \"node:fs\"; im",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/nightly/pipeline.ts",
        "line": 9,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/nlm/client.ts)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/nlm/client.ts:8`): 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/nlm/client.ts"
      },
      "evidence": "{ execFile } from \"node:child_process\"; import { promisify } from \"node:util\"; import type { NlmNotebook, NlmQueryResult",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/nlm/client.ts",
        "line": 8,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (dist/setup.js)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`dist/setup.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/setup.js"
      },
      "evidence": "{ execSync } from \"node:child_process\"; import { OLLAMA_URL, OLLAMA_CHAT_MODEL, OLLAMA_EMBED_MODEL } from \"./config.js\";",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "dist/setup.js",
        "line": 1,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (src/setup.ts)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/setup.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/setup.ts"
      },
      "evidence": "{ execSync } from \"node:child_process\"; import { OLLAMA_URL, OLLAMA_CHAT_MODEL, OLLAMA_EMBED_MODEL } from \"./config.js\";",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/setup.ts",
        "line": 1,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SUP-010",
      "title": "Package runs install-time scripts (postinstall)",
      "category": "supply-chain",
      "severity": "low",
      "confidence": "heuristic",
      "description": "\"inkstone-mcp\" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.",
      "remediation": "Review the scripts; install with --ignore-scripts where possible and vet what they do.",
      "location": {
        "kind": "package",
        "name": "inkstone-mcp"
      },
      "evidence": "node -e \"console.log('\\n  Inkstone installed! Run \\x1b[1minkstone setup\\x1b[0m to check prerequisites (Ollama, Gemma 4, embeddings).\\n')\"",
      "owasp": "LLM03:2025 Supply Chain",
      "references": [
        "https://github.com/ossf/package-analysis",
        "https://owasp.org/www-project-top-10-ci-cd-security-risks/"
      ],
      "data": {
        "scripts": [
          "postinstall"
        ]
      }
    },
    {
      "ruleId": "MTC-SUP-011",
      "title": "Package declares no source repository",
      "category": "supply-chain",
      "severity": "info",
      "confidence": "strong",
      "description": "\"inkstone-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
      "remediation": "Prefer packages that link to public, reviewable source.",
      "location": {
        "kind": "package",
        "name": "inkstone-mcp"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "memory_search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_deep_query",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_hybrid_answer",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_nlm_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_write",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_get",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_dream",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_goals",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_failures",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_contradictions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_hypotheses",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_self_model",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_consolidate",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_global_search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_summarize",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_nlm_sync",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_nlm_query",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "user_create",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "user_list",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "user_remove",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "namespace_grant",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "namespace_revoke",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_graph_neighbors",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_graph_path",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_graph_contradictions",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_graph_context",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_graph_centrality",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_gemini_sync",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "memory_gemini_query",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "f89bd879a6bccec1e62da53b668b06be6d45d9e962fdc84770ee66d0e82e0810",
  "stats": {
    "tools": 29,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 6,
      "medium": 0,
      "low": 3,
      "info": 1
    }
  }
}