Skip to content

🔒 Fix SQL injection vulnerability in DuckDB execute #35

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
devdudumuniz wants to merge 1 commit into
base: main
Choose a base branch
from
+9 −14
Draft

🔒 Fix SQL injection vulnerability in DuckDB execute #35

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 9 additions & 14 deletions pysus/api/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -820,14 +820,13 @@ def read_parquet(

def get_columns(path: Path) -> set[tuple[str, str]]:
"""Return the schema of a Parquet file as (name, type) pairs."""
result = duckdb.execute(f"SELECT * FROM '{path}' LIMIT 0")
result = duckdb.execute(
"SELECT * FROM read_parquet($1) LIMIT 0", [[str(path)]]
)
return {(col[0], str(col[1])) for col in result.description}

if len(paths) == 1:
query = f"SELECT * FROM '{paths[0]}'"
else:
paths_str = ", ".join(f"'{p}'" for p in paths)
query = f"SELECT * FROM read_parquet([{paths_str}])"
params = [[str(p) for p in paths]]
query = "SELECT * FROM read_parquet($1)"

schemas = [get_columns(p) for p in paths]
common_columns = set.intersection(*schemas) if schemas else set()
Expand All @@ -847,22 +846,18 @@ def get_columns(path: Path) -> set[tuple[str, str]]:
if not common_columns:
return duckdb.execute("SELECT * WHERE 1=0")
cols = ", ".join(f'"{c[0]}"' for c in sorted(common_columns))
paths_str = ", ".join(f"'{p}'" for p in paths)
query = f"SELECT {cols} FROM read_parquet([{paths_str}])"
query = f"SELECT {cols} FROM read_parquet($1)"

else:
paths_str = ", ".join(f"'{p}'" for p in paths)
query = (
f"SELECT * FROM read_parquet([{paths_str}], union_by_name=True)"
)
query = "SELECT * FROM read_parquet($1, union_by_name=True)"

if sql:
if sql.upper().startswith("SELECT"):
query = sql.replace("FROM t", f"FROM ({query}) AS t")
else:
query = f"SELECT {sql} FROM ({query}) AS t"

base = duckdb.execute(query)
base = duckdb.execute(query, params)

if not add_dv:
return base
Expand Down Expand Up @@ -890,4 +885,4 @@ def get_columns(path: Path) -> set[tuple[str, str]]:
for c in base.description
]
query = f"SELECT {', '.join(selects)} FROM ({query}) AS _t"
return duckdb.execute(query)
return duckdb.execute(query, params)