Raw scan report

Ds — 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": "ds-mcp-server",
    "source": {
      "kind": "package",
      "origin": "ds-mcp-server"
    },
    "server": {
      "name": "ds-mcp-server"
    }
  },
  "grade": "B",
  "score": {
    "score": 89,
    "threatScore": 100,
    "grade": "B",
    "band": "B",
    "categorySubtotals": {
      "injection": 0,
      "exfiltration": 0,
      "permissions": 0,
      "supply-chain": 0,
      "network": 0,
      "hygiene": 0
    },
    "vector": [
      {
        "kind": "client",
        "term": "capability-exposure",
        "level": "critical",
        "label": "capability blast radius (critical) — client exposure if the model is manipulated",
        "appliedPenalty": 10
      },
      {
        "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": "critical",
    "reasons": [
      "ingests untrusted external content (a prompt-injection entry point)",
      "can send data / act on an external service",
      "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",
      "untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
      "untrusted input can reach code execution"
    ],
    "tags": [
      "external-sink",
      "code-exec",
      "sensitive-source",
      "file-write",
      "untrusted-input"
    ]
  },
  "coverage": {
    "level": "source",
    "inputs": {
      "toolSurface": true,
      "implementationSource": true,
      "packageMetadata": true,
      "liveTransport": false
    },
    "caveats": [
      "Tools were statically extracted from the published source (49 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-002",
      "title": "Completed toxic-flow trifecta across tools",
      "category": "exfiltration",
      "severity": "critical",
      "confidence": "strong",
      "description": "This server (without client built-ins) exposes a complete data-exfiltration chain: fetch_webpage → github_read_file → http_request. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
      "remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
      "location": {
        "kind": "flow",
        "name": "fetch_webpage → github_read_file → http_request"
      },
      "owasp": "LLM02:2025 Sensitive Information Disclosure",
      "references": [],
      "data": {
        "untrusted": [
          "fetch_webpage",
          "search_web",
          "wikipedia",
          "youtube_transcript"
        ],
        "sources": [
          "read_file",
          "github_read_file"
        ],
        "sinks": [
          "run_background_process",
          "http_request",
          "run_shell_command"
        ],
        "path": [
          "fetch_webpage",
          "github_read_file",
          "http_request"
        ],
        "edges": [
          {
            "from": "fetch_webpage",
            "to": "github_read_file",
            "kind": "agent-mediated"
          },
          {
            "from": "github_read_file",
            "to": "http_request",
            "kind": "agent-mediated"
          }
        ],
        "wired": false
      }
    },
    {
      "ruleId": "MTC-CAP-001",
      "title": "Tool \"run_shell_command\" exposes command/code execution",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "Tool \"run_shell_command\" appears to run shell commands or evaluate code (keyword \"shell\" 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": "run_shell_command"
      },
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (src/ds_mcp_server/_tools/plot_interactive.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/ds_mcp_server/_tools/plot_interactive.py:407`): 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": "src/ds_mcp_server/_tools/plot_interactive.py"
      },
      "evidence": "rt modules, call open()/eval()/exec(), or access dunder attributes.\" ) except SandboxTimeout as exc:",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "src/ds_mcp_server/_tools/plot_interactive.py",
        "line": 407,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (src/ds_mcp_server/_tools/plot_static.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/ds_mcp_server/_tools/plot_static.py:226`): 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": "src/ds_mcp_server/_tools/plot_static.py"
      },
      "evidence": "rt modules, call open()/eval()/exec(), or access dunder attributes.\" ) except SandboxTimeout as exc:",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "src/ds_mcp_server/_tools/plot_static.py",
        "line": 226,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-001",
      "title": "Dynamic code execution in server code (src/ds_mcp_server/server.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/ds_mcp_server/server.py:44`): 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": "src/ds_mcp_server/server.py"
      },
      "evidence": "eges — imports, open(), eval(),\", \"!! subprocess, etc. are all allowed.\", \"!!\", \"!! A hostile da",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-001",
        "file": "src/ds_mcp_server/server.py",
        "line": 44,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/ds_mcp_server/_tools/plot_interactive.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/ds_mcp_server/_tools/plot_interactive.py:407`): 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/ds_mcp_server/_tools/plot_interactive.py"
      },
      "evidence": "les, call open()/eval()/exec(), or access dunder attributes.\" ) except SandboxTimeout as exc:",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/ds_mcp_server/_tools/plot_interactive.py",
        "line": 407,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/ds_mcp_server/_tools/plot_static.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/ds_mcp_server/_tools/plot_static.py:226`): 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/ds_mcp_server/_tools/plot_static.py"
      },
      "evidence": "les, call open()/eval()/exec(), or access dunder attributes.\" ) except SandboxTimeout as exc:",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/ds_mcp_server/_tools/plot_static.py",
        "line": 226,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/ds_mcp_server/_tools/sandbox.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/ds_mcp_server/_tools/sandbox.py:5`): 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/ds_mcp_server/_tools/sandbox.py"
      },
      "evidence": "oduced by the LLM and `exec()` it in-process. Because the LLM's input can be influenced by any file, webpage, or datas",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/ds_mcp_server/_tools/sandbox.py",
        "line": 5,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in server code (src/ds_mcp_server/_tools/system_tools.py)",
      "category": "permissions",
      "severity": "high",
      "confidence": "strong",
      "description": "In the server's implementation (`src/ds_mcp_server/_tools/system_tools.py:29`): 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/ds_mcp_server/_tools/system_tools.py"
      },
      "evidence": "r(\"~\") result = subprocess.run( command, shell=True, capture_output=True,",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "src/ds_mcp_server/_tools/system_tools.py",
        "line": 29,
        "nonRuntime": false
      }
    },
    {
      "ruleId": "MTC-CAP-002",
      "title": "Tool \"write_file\" can modify the filesystem",
      "category": "permissions",
      "severity": "medium",
      "confidence": "strong",
      "description": "Tool \"write_file\" can write, overwrite or delete files (keyword \"write_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": "write_file"
      },
      "data": {
        "tags": [
          "file-write"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"run_shell_command\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"run_shell_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": "run_shell_command"
      },
      "data": {
        "tags": [
          "code-exec"
        ]
      }
    },
    {
      "ruleId": "MTC-CAP-005",
      "title": "Mutating tool \"write_file\" declares no destructiveHint",
      "category": "hygiene",
      "severity": "low",
      "confidence": "heuristic",
      "description": "Tool \"write_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": "write_file"
      },
      "data": {
        "tags": [
          "file-write"
        ]
      }
    },
    {
      "ruleId": "MTC-SRC-002",
      "title": "Shell/command execution in packaging/dev tooling (tests/test_sandbox.py)",
      "category": "permissions",
      "severity": "low",
      "confidence": "heuristic",
      "description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_sandbox.py:40`): 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": "tests/test_sandbox.py"
      },
      "evidence": "('1+1')\", \"exec('x=1')\", \"compile('x','<s>','exec')\", \"open('/etc/passwd')\",",
      "owasp": "LLM05:2025 Improper Output Handling",
      "data": {
        "rule": "MTC-SRC-002",
        "file": "tests/test_sandbox.py",
        "line": 40,
        "nonRuntime": true
      }
    }
  ],
  "toxicFlows": [
    {
      "id": "flow-1",
      "severity": "critical",
      "confidence": "strong",
      "untrustedInput": [
        "fetch_webpage",
        "search_web",
        "wikipedia",
        "youtube_transcript"
      ],
      "sensitiveSource": [
        "read_file",
        "github_read_file"
      ],
      "externalSink": [
        "run_background_process",
        "http_request",
        "run_shell_command"
      ],
      "selfContained": false,
      "path": [
        "fetch_webpage",
        "github_read_file",
        "http_request"
      ],
      "pathWired": false,
      "description": "A cross-tool exfiltration chain exists: fetch_webpage → github_read_file → http_request."
    }
  ],
  "capabilities": [
    {
      "tool": "plot_interactive_histogram",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_interactive_scatterplot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_interactive_boxplot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_interactive_lineplot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_interactive_correlation_heatmap",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_interactive_barchart",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_interactive_scatter_matrix",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "generate_custom_plotly",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_all_columns_summary",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "get_column_summary",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_static_histogram",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_static_scatterplot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_static_boxplot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_static_lineplot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_static_barchart",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "generate_custom_static_plot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_static_pairplot",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_static_wordcloud",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "plot_static_correlation_heatmap",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "run_correlation",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "run_group_comparison",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "run_linear_regression",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "rank_target_correlations",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "patch_file",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "run_background_process",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"http_request\""
        ]
      }
    },
    {
      "tool": "stop_background_process",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "list_background_processes",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "http_request",
      "tags": [
        "external-sink"
      ],
      "reasons": {
        "external-sink": [
          "keyword \"http_request\""
        ]
      }
    },
    {
      "tool": "find_in_files",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "run_shell_command",
      "tags": [
        "code-exec"
      ],
      "reasons": {
        "code-exec": [
          "keyword \"shell\" in tool name"
        ]
      }
    },
    {
      "tool": "read_file",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"read_file\""
        ]
      }
    },
    {
      "tool": "write_file",
      "tags": [
        "file-write"
      ],
      "reasons": {
        "file-write": [
          "keyword \"write_file\" in tool name"
        ]
      }
    },
    {
      "tool": "list_directory",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "fetch_webpage",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "search_web",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"web_search\""
        ]
      }
    },
    {
      "tool": "screenshot_webpage",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "arxiv_search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "github_search",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "github_read_file",
      "tags": [
        "sensitive-source"
      ],
      "reasons": {
        "sensitive-source": [
          "keyword \"read_file\""
        ]
      }
    },
    {
      "tool": "wikipedia",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "youtube_transcript",
      "tags": [
        "untrusted-input"
      ],
      "reasons": {
        "untrusted-input": [
          "keyword \"fetch\""
        ]
      }
    },
    {
      "tool": "screenshot_webpages",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_pdf",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "extract_tables_from_pdf",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_docx",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "read_excel_sheets",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "ocr_image",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "summarize_document",
      "tags": [],
      "reasons": {}
    },
    {
      "tool": "profile_dataset",
      "tags": [],
      "reasons": {}
    }
  ],
  "surfaceDigest": "6c3560516e70befd47175942d85ad3699804a1b1353343af10941e428852c232",
  "stats": {
    "tools": 49,
    "prompts": 0,
    "resources": 0,
    "findingsBySeverity": {
      "critical": 1,
      "high": 8,
      "medium": 1,
      "low": 3,
      "info": 0
    }
  }
}