DATA
6de0bf9f5b
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.
42 lines
1.1 KiB
Python
42 lines
1.1 KiB
Python
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)
|