Raw scan report

Writing — 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": "@hanna84/mcp-writing",
    "source": {
      "kind": "package",
      "origin": "@hanna84/mcp-writing"
    },
    "server": {
      "name": "@hanna84/mcp-writing"
    }
  },
  "grade": "A",
  "score": {
    "score": 94,
    "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": "source",
        "label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
        "appliedPenalty": 0
      },
      {
        "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 (72 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 (bin/mcp-writing.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`bin/mcp-writing.js: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": "bin/mcp-writing.js"
      },
      "evidence": "rt { spawn } from \"node:child_process\"; import path from \"node:path\"; import { fileURLToPath, pathToFileURL } from \"node",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "bin/mcp-writing.js",
        "line": 3,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/core/git.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/core/git.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": "src/core/git.js"
      },
      "evidence": ", execSync } from \"node:child_process\"; import fs from \"node:fs\"; import path from \"node:path\"; /** * Check if a direc",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/core/git.js",
        "line": 1,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/runtime/async-jobs.js)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/runtime/async-jobs.js: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/runtime/async-jobs.js"
      },
      "evidence": "rt { spawn } from \"node:child_process\"; import { randomUUID } from \"node:crypto\"; import { ASYNC_PROGRESS_PREFIX } from",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/runtime/async-jobs.js",
        "line": 3,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (src/scripts/manual-validation.mjs)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/scripts/manual-validation.mjs:4`): 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/scripts/manual-validation.mjs"
      },
      "evidence": "rt { spawn } from \"node:child_process\"; import { Client } from \"@modelcontextprotocol/sdk/client/index.js\"; import { SSE",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/scripts/manual-validation.mjs",
        "line": 4,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (src/scripts/mcp-debug-client.mjs)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/scripts/mcp-debug-client.mjs: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/scripts/mcp-debug-client.mjs"
      },
      "evidence": "rt { spawn } from \"node:child_process\"; import { Client } from \"@modelcontextprotocol/sdk/client/index.js\"; import { SSE",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/scripts/mcp-debug-client.mjs",
        "line": 1,
        "nonRuntime": true
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "describe_workflows",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_runtime_config",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": " to the matching ",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "propose_edit",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "commit_edit",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "discard_edit",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "snapshot_scene",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_snapshots",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_character_sheet",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_place_sheet",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "track_thread_arc",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "upsert_thread_link",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "link_reference_evidence",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "upsert_reference_link",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "connect_character_place_evidence",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "connect_scene_character_evidence",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "connect_scene_place_evidence",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "record_character_relationship_beat",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "audit_relationship_metadata",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_chapter",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "rename_chapter",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "reorder_chapter",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "attach_epigraph",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "move_scene",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "assign_scene_to_chapter",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_scene_metadata",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_character_sheet",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_place_sheet",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "flag_scene",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "preview_review_bundle",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_review_bundle",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "find_scenes",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_scene_prose",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_chapter_prose",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_chapters",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "find_epigraphs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_arc",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_characters",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_character_sheet",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_places",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_place_sheet",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_metadata",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "search_reference",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_scene_references",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_reference_doc",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_threads",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_thread_arc",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_relationship_arc",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "suggest_scene_references",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "setup_prose_styleguide_config",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_prose_styleguide_config",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "summarize_prose_styleguide_config",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "bootstrap_prose_styleguide_config",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_prose_styleguide_config",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "preview_prose_styleguide_config_update",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "check_prose_styleguide_drift",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "setup_prose_styleguide_skill",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "sync",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "diagnose_structure",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "export_structure_snapshot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "export_project_backup",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "diagnose_project_backups",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "restore_structure_from_export",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "restore_project_from_backup",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "import_scrivener_sync",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "import_scrivener_sync_async",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "merge_scrivener_project_beta",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "enrich_scene_characters_batch",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_async_job_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_async_jobs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "cancel_async_job",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "enrich_scene",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "7b44a8f0177d1ce4b886de621f54cfb422f35d25469ac5c564e07167f5253cb9",
  "stats": {
    "tools": 72,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 3,
      "medium": 0,
      "low": 2,
      "info": 0
    }
  }
}