feat: make sure to quote formulas on Excel export (apache#31166)

superset/utils/excel.py

@@ -22,9 +22,30 @@
 from superset.utils.core import GenericDataType
 
 
+def quote_formulas(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Make sure to quote any formulas for security reasons.
+    """
+    formula_prefixes = {"=", "+", "-", "@"}
+
+    for col in df.select_dtypes(include="object").columns:
+        df[col] = df[col].apply(
+            lambda x: (
+                f"'{x}"
+                if isinstance(x, str) and len(x) and x[0] in formula_prefixes
+                else x
+            )
+        )
+
+    return df
+
+
 def df_to_excel(df: pd.DataFrame, **kwargs: Any) -> Any:
     output = io.BytesIO()
 
+    # make sure formulas are quoted, to prevent malicious injections
+    df = quote_formulas(df)
+
     # pylint: disable=abstract-class-instantiated
     with pd.ExcelWriter(output, engine="xlsxwriter") as writer:
         df.to_excel(writer, **kwargs)

tests/unit_tests/utils/excel_tests.py

@@ -34,6 +34,19 @@ def test_timezone_conversion() -> None:
     assert pd.read_excel(contents)["dt"][0] == "2023-01-01 00:00:00+00:00"
 
 
+def test_quote_formulas() -> None:
+    """
+    Test that formulas are quoted in Excel.
+    """
+    df = pd.DataFrame({"formula": ["=SUM(A1:A2)", "normal", "@SUM(A1:A2)"]})
+    contents = df_to_excel(df)
+    assert pd.read_excel(contents)["formula"].tolist() == [
+        "'=SUM(A1:A2)",
+        "normal",
+        "'@SUM(A1:A2)",
+    ]
+
+
 def test_column_data_types_with_one_numeric_column():
     df = pd.DataFrame(
         {