Raw scan report

Databricks Mcp Genie — 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": "databricks-mcp-genie",
    "source": {
      "kind": "package",
      "origin": "databricks-mcp-genie"
    },
    "server": {
      "name": "databricks-mcp-genie"
    }
  },
  "grade": "A",
  "score": {
    "score": 92,
    "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": "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 (21 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 (.claude/skills/document-skills/xlsx/recalc.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`.claude/skills/document-skills/xlsx/recalc.py:31`): 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": ".claude/skills/document-skills/xlsx/recalc.py"
      },
      "evidence": "sts(macro_dir): subprocess.run(['soffice', '--headless', '--terminate_after_init'], captu",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": ".claude/skills/document-skills/xlsx/recalc.py",
        "line": 31,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (.claude/skills/document-skills/docx/ooxml/scripts/pack.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/document-skills/docx/ooxml/scripts/pack.py:103`): 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": ".claude/skills/document-skills/docx/ooxml/scripts/pack.py"
      },
      "evidence": "y: result = subprocess.run( [ \"soffice\", \"--headless",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": ".claude/skills/document-skills/docx/ooxml/scripts/pack.py",
        "line": 103,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (.claude/skills/document-skills/docx/ooxml/scripts/validation/redlining.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/document-skills/docx/ooxml/scripts/validation/redlining.py:153`): 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": ".claude/skills/document-skills/docx/ooxml/scripts/validation/redlining.py"
      },
      "evidence": "result = subprocess.run( [ \"git\", \"di",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": ".claude/skills/document-skills/docx/ooxml/scripts/validation/redlining.py",
        "line": 153,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (.claude/skills/document-skills/pptx/ooxml/scripts/pack.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/document-skills/pptx/ooxml/scripts/pack.py:103`): 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": ".claude/skills/document-skills/pptx/ooxml/scripts/pack.py"
      },
      "evidence": "y: result = subprocess.run( [ \"soffice\", \"--headless",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": ".claude/skills/document-skills/pptx/ooxml/scripts/pack.py",
        "line": 103,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (.claude/skills/document-skills/pptx/ooxml/scripts/validation/redlining.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/document-skills/pptx/ooxml/scripts/validation/redlining.py:153`): 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": ".claude/skills/document-skills/pptx/ooxml/scripts/validation/redlining.py"
      },
      "evidence": "result = subprocess.run( [ \"git\", \"di",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": ".claude/skills/document-skills/pptx/ooxml/scripts/validation/redlining.py",
        "line": 153,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (.claude/skills/document-skills/pptx/scripts/thumbnail.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/document-skills/pptx/scripts/thumbnail.py:219`): 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": ".claude/skills/document-skills/pptx/scripts/thumbnail.py"
      },
      "evidence": "o PDF...\") result = subprocess.run( [ \"soffice\", \"--headless\", \"--conver",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": ".claude/skills/document-skills/pptx/scripts/thumbnail.py",
        "line": 219,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (.claude/skills/webapp-testing/scripts/with_server.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/webapp-testing/scripts/with_server.py:69`): 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": ".claude/skills/webapp-testing/scripts/with_server.py"
      },
      "evidence": "& process = subprocess.Popen( server['cmd'], shell=True, std",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": ".claude/skills/webapp-testing/scripts/with_server.py",
        "line": 69,
        "nonRuntime": true
      }
    },
    {
      "ruleId": "MTC-SUP-011",
      "title": "Package declares no source repository",
      "category": "supply-chain",
      "severity": "info",
      "confidence": "strong",
      "description": "\"databricks-mcp-genie\" 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": "databricks-mcp-genie"
      }
    }
  ],
  "toxicFlows": [],
  "capabilities": [
    {
      "tool": "list_clusters",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_jobs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_job",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "delete_job",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_run_status",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_job_runs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "cancel_run",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "dbfs_put",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "install_library",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "uninstall_library",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_cluster_libraries",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "update_repo",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_repos",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_catalogs",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_catalog",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_schemas",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_schema",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_tables",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "create_table",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_table_lineage",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_genie_spaces",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "375d965f3c2958f721d5e2b305d2d2f683db7a0028a1c211b706148efb0903cc",
  "stats": {
    "tools": 21,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 0,
      "high": 1,
      "medium": 0,
      "low": 6,
      "info": 1
    }
  }
}