Initial commit: hardened DeerFlow factory

Vendored deer-flow upstream (bytedance/deer-flow) plus prompt-injection
hardening:

- New deerflow.security package: content_delimiter, html_cleaner,
  sanitizer (8 layers — invisible chars, control chars, symbols, NFC,
  PUA, tag chars, horizontal whitespace collapse with newline/tab
  preservation, length cap)
- New deerflow.community.searx package: web_search, web_fetch,
  image_search backed by a private SearX instance, every external
  string sanitized and wrapped in <<<EXTERNAL_UNTRUSTED_CONTENT>>>
  delimiters
- All native community web providers (ddg_search, tavily, exa,
  firecrawl, jina_ai, infoquest, image_search) replaced with hard-fail
  stubs that raise NativeWebToolDisabledError at import time, so a
  misconfigured tool.use path fails loud rather than silently falling
  back to unsanitized output
- Native client back-doors (jina_client.py, infoquest_client.py)
  stubbed too
- Native-tool tests quarantined under tests/_disabled_native/
  (collect_ignore_glob via local conftest.py)
- Sanitizer Layer 7 fix: only collapse horizontal whitespace, preserve
  newlines and tabs so list/table structure survives
- Hardened runtime config.yaml references only the searx-backed tools
- Factory overlay (backend/) kept in sync with deer-flow tree as a
  reference / source

See HARDENING.md for the full audit trail and verification steps.

deer-flow/backend/tests/test_skills_archive_root.py

@@ -0,0 +1,41 @@
+from pathlib import Path
+
+import pytest
+
+from deerflow.skills.installer import resolve_skill_dir_from_archive
+
+
+def _write_skill(skill_dir: Path) -> None:
+    skill_dir.mkdir(parents=True, exist_ok=True)
+    (skill_dir / "SKILL.md").write_text(
+        """---
+name: demo-skill
+description: Demo skill
+---
+
+# Demo Skill
+""",
+        encoding="utf-8",
+    )
+
+
+def test_resolve_skill_dir_ignores_macosx_wrapper(tmp_path: Path) -> None:
+    _write_skill(tmp_path / "demo-skill")
+    (tmp_path / "__MACOSX").mkdir()
+
+    assert resolve_skill_dir_from_archive(tmp_path) == tmp_path / "demo-skill"
+
+
+def test_resolve_skill_dir_ignores_hidden_top_level_entries(tmp_path: Path) -> None:
+    _write_skill(tmp_path / "demo-skill")
+    (tmp_path / ".DS_Store").write_text("metadata", encoding="utf-8")
+
+    assert resolve_skill_dir_from_archive(tmp_path) == tmp_path / "demo-skill"
+
+
+def test_resolve_skill_dir_rejects_archive_with_only_metadata(tmp_path: Path) -> None:
+    (tmp_path / "__MACOSX").mkdir()
+    (tmp_path / ".DS_Store").write_text("metadata", encoding="utf-8")
+
+    with pytest.raises(ValueError, match="empty"):
+        resolve_skill_dir_from_archive(tmp_path)