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.
72 lines
2.6 KiB
Python
72 lines
2.6 KiB
Python
"""Tests for prompt injection sanitizer."""
|
|
|
|
import pytest
|
|
from deerflow.security.sanitizer import PromptInjectionSanitizer
|
|
|
|
|
|
class TestPromptInjectionSanitizer:
|
|
"""Test cases based on OpenClaw patterns."""
|
|
|
|
def test_removes_zero_width_spaces(self):
|
|
"""Zero-width characters are common steganography vectors."""
|
|
sanitizer = PromptInjectionSanitizer()
|
|
text = "Hello\u200bWorld\u200c" # ZWSP and ZWNJ
|
|
result = sanitizer.sanitize(text)
|
|
assert "\u200b" not in result
|
|
assert "\u200c" not in result
|
|
assert result == "HelloWorld"
|
|
|
|
def test_removes_control_chars(self):
|
|
"""Control chars can disrupt prompt parsing."""
|
|
sanitizer = PromptInjectionSanitizer()
|
|
text = "Hello\x00World\x01Test"
|
|
result = sanitizer.sanitize(text)
|
|
assert "\x00" not in result
|
|
assert "\x01" not in result
|
|
assert "Hello" in result
|
|
|
|
def test_preserves_newlines_and_tabs(self):
|
|
"""Structural characters should be preserved."""
|
|
sanitizer = PromptInjectionSanitizer()
|
|
text = "Line1\nLine2\tTabbed"
|
|
result = sanitizer.sanitize(text)
|
|
assert "\n" in result
|
|
assert "\t" in result
|
|
|
|
def test_truncates_long_content(self):
|
|
"""Length limiting prevents context overflow."""
|
|
sanitizer = PromptInjectionSanitizer()
|
|
text = "A" * 1000
|
|
result = sanitizer.sanitize(text, max_length=100)
|
|
assert len(result) == 100
|
|
assert result.endswith("...")
|
|
|
|
def test_handles_pua_characters(self):
|
|
"""Private Use Area chars can encode hidden data."""
|
|
sanitizer = PromptInjectionSanitizer()
|
|
text = "Hello\uE000World" # PUA start
|
|
result = sanitizer.sanitize(text)
|
|
assert "\uE000" not in result
|
|
|
|
|
|
class TestContentDelimiter:
|
|
"""Test delimiter wrapping."""
|
|
|
|
def test_wraps_dict_content(self):
|
|
from deerflow.security.content_delimiter import wrap_untrusted_content
|
|
|
|
content = {"title": "Test", "url": "http://example.com"}
|
|
result = wrap_untrusted_content(content)
|
|
|
|
assert "<<<EXTERNAL_UNTRUSTED_CONTENT>>>" in result
|
|
assert "<<<END_EXTERNAL_UNTRUSTED_CONTENT>>>" in result
|
|
assert "Test" in result
|
|
|
|
def test_wraps_string_content(self):
|
|
from deerflow.security.content_delimiter import wrap_untrusted_content
|
|
|
|
content = "Raw text from web"
|
|
result = wrap_untrusted_content(content)
|
|
|
|
assert "<<<EXTERNAL_UNTRUSTED_CONTENT>>>" in result
|
|
assert "Raw text from web" in result |