From 575c2b79f92aeded7490cf94b31cea5341248b53 Mon Sep 17 00:00:00 2001
From: Miguel Jacq <mig@mig5.net>
Date: Wed, 1 Jul 2026 12:23:19 +1000
Subject: [PATCH] Fix catching of defusedxml exception

---
 src/jinjaturtle/cli.py            | 15 +++++++++++
 tests/test_config_parse_errors.py | 41 +++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+)

diff --git a/src/jinjaturtle/cli.py b/src/jinjaturtle/cli.py
index 65dfa72..d901606 100644
--- a/src/jinjaturtle/cli.py
+++ b/src/jinjaturtle/cli.py
@@ -3,6 +3,7 @@ from __future__ import annotations
 import argparse
 import sys
 from defusedxml import defuse_stdlib
+from defusedxml.common import DefusedXmlException
 from pathlib import Path
 
 from . import j2
@@ -77,6 +78,20 @@ def _main(argv: list[str] | None = None) -> int:
     except OutputPathError as exc:
         print(f"jinjaturtle: refusing unsafe output path: {exc}", file=sys.stderr)
         return 2
+    except DefusedXmlException as exc:
+        # defusedxml rejected the XML because it attempted a DTD, entity
+        # expansion, or external reference (XXE / billion-laughs class attack).
+        # This is a deliberately-blocked attack, not a benign malformed file, so
+        # core.parse_config lets it propagate unchanged rather than folding it
+        # into ConfigParseError. Report it as a refused unsafe input with a
+        # non-zero exit code instead of leaking an internal traceback.
+        print(
+            "jinjaturtle: refusing unsafe XML input: the document uses a DTD, "
+            f"entity expansion, or external reference ({exc.__class__.__name__}). "
+            "This is blocked to prevent XXE / entity-expansion attacks.",
+            file=sys.stderr,
+        )
+        return 2
     except ConfigParseError as exc:
         # The source file could not be parsed as its (detected or forced)
         # format. This is expected for malformed/attacker-influenced input;
diff --git a/tests/test_config_parse_errors.py b/tests/test_config_parse_errors.py
index ab42fe5..01ba1ef 100644
--- a/tests/test_config_parse_errors.py
+++ b/tests/test_config_parse_errors.py
@@ -106,6 +106,47 @@ def test_cli_fails_cleanly_on_malformed_xml(tmp_path: Path) -> None:
     assert "Traceback (most recent call last)" not in res.stderr
 
 
+@pytest.mark.parametrize(
+    "content",
+    [
+        # Classic XXE: external SYSTEM entity used to read a local file.
+        (
+            '<?xml version="1.0"?>\n'
+            '<!DOCTYPE root [<!ENTITY xxe SYSTEM "file:///etc/hostname">]>\n'
+            "<root>&xxe;</root>\n"
+        ),
+        # Billion-laughs style internal entity expansion.
+        (
+            '<?xml version="1.0"?>\n'
+            '<!DOCTYPE lolz [<!ENTITY lol "lol"><!ENTITY lol2 "&lol;&lol;&lol;">]>\n'
+            "<lolz>&lol2;</lolz>\n"
+        ),
+        # External parameter entity (SSRF / out-of-band XXE vector).
+        (
+            '<?xml version="1.0"?>\n'
+            '<!DOCTYPE root [<!ENTITY % ext SYSTEM "http://127.0.0.1:9/x.dtd"> %ext;]>\n'
+            "<root>x</root>\n"
+        ),
+    ],
+)
+def test_cli_refuses_xxe_cleanly(tmp_path: Path, content: str) -> None:
+    """defusedxml's security refusal must surface as a clean non-zero exit.
+
+    ``EntitiesForbidden``/``DTDForbidden``/``ExternalReferenceForbidden`` subclass
+    ``DefusedXmlException`` (and ``ValueError``). ``parse_config`` deliberately
+    lets them propagate rather than folding them into ``ConfigParseError`` so a
+    blocked attack stays distinguishable from a benign malformed file. The CLI
+    must therefore catch ``DefusedXmlException`` itself and exit cleanly instead
+    of leaking a Python traceback.
+    """
+    src = tmp_path / "xxe.xml"
+    src.write_text(content, encoding="utf-8")
+    res = _run_cli([str(src), "-f", "xml", "-r", "demo"])
+    assert res.returncode == 2
+    assert "refusing unsafe XML input" in res.stderr
+    assert "Traceback (most recent call last)" not in res.stderr
+
+
 def test_folder_mode_skips_unparseable_file(tmp_path: Path) -> None:
     """One malformed file should not abort processing of the whole directory."""
     from jinjaturtle.multi import process_directory