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.

backend/packages/harness/deerflow/community/searx/__init__.py

@@ -0,0 +1 @@
+"""Hardened SearX provider for DeerFlow."""

backend/packages/harness/deerflow/community/searx/tools.py

@@ -0,0 +1,98 @@
+"""Hardened SearX web search and fetch tools."""
+
+import json
+import os
+from urllib.parse import quote
+
+import httpx
+from langchain.tools import tool
+
+from deerflow.config import get_app_config
+from deerflow.security.content_delimiter import wrap_untrusted_content
+from deerflow.security.sanitizer import sanitizer
+from deerflow.security.html_cleaner import extract_secure_text
+
+
+def _get_searx_config() -> dict:
+    """Get SearX configuration from app config."""
+    config = get_app_config().get_tool_config("web_search")
+    return {
+        "url": config.model_extra.get("searx_url", "http://localhost:8888"),
+        "max_results": config.model_extra.get("max_results", 10),
+    }
+
+
+@tool("web_search", parse_docstring=True)
+def web_search_tool(query: str, max_results: int = 10) -> str:
+    """Search the web using hardened SearX instance.
+    
+    All results are sanitized against prompt injection attacks.
+    
+    Args:
+        query: Search keywords
+        max_results: Maximum results to return (default 10)
+    """
+    cfg = _get_searx_config()
+    searx_url = cfg["url"]
+    
+    # URL-safe encoding
+    encoded_query = quote(query)
+    
+    try:
+        response = httpx.get(
+            f"{searx_url}/search",
+            params={
+                "q": encoded_query,
+                "format": "json",
+                "max_results": min(max_results, cfg["max_results"]),
+            },
+            timeout=30.0
+        )
+        response.raise_for_status()
+        data = response.json()
+    except Exception as e:
+        return wrap_untrusted_content({"error": f"Search failed: {e}"})
+    
+    # Sanitize and limit results
+    results = []
+    for r in data.get("results", [])[:max_results]:
+        results.append({
+            "title": sanitizer.sanitize(r.get("title", "")),
+            "url": r.get("url", ""),  # Keep URL intact
+            "content": sanitizer.sanitize(r.get("content", ""), max_length=500),
+        })
+    
+    output = {
+        "query": query,
+        "total_results": len(results),
+        "results": results,
+    }
+    
+    # Wrap with security delimiters
+    return wrap_untrusted_content(output)
+
+
+@tool("web_fetch", parse_docstring=True)
+async def web_fetch_tool(url: str, max_chars: int = 10000) -> str:
+    """Fetch web page content with security hardening.
+    
+    Dangerous HTML elements are stripped and content is sanitized.
+    
+    Args:
+        url: URL to fetch
+        max_chars: Maximum characters to return (default 10000)
+    """
+    try:
+        async with httpx.AsyncClient() as client:
+            response = await client.get(url, timeout=30.0)
+            response.raise_for_status()
+            html = response.text
+    except Exception as e:
+        return wrap_untrusted_content({"error": f"Fetch failed: {e}"})
+    
+    # Extract text and sanitize
+    raw_text = extract_secure_text(html)
+    clean_text = sanitizer.sanitize(raw_text, max_length=max_chars)
+    
+    # Wrap with security delimiters
+    return wrap_untrusted_content(clean_text)

backend/packages/harness/deerflow/security/content_delimiter.py

@@ -0,0 +1,44 @@
+"""Content delimiter wrapper for safe LLM prompt integration."""
+
+from typing import Union
+import json
+
+
+# OpenClaw-style delimiters
+START_DELIMITER = "<<<EXTERNAL_UNTRUSTED_CONTENT>>>"
+END_DELIMITER = "<<<END_EXTERNAL_UNTRUSTED_CONTENT>>>"
+
+
+def wrap_untrusted_content(content: Union[str, dict, list]) -> str:
+    """Wrap external content with safety delimiters.
+    
+    This creates a semantic boundary between system instructions
+    and untrusted external data, helping prevent prompt injection.
+    
+    Args:
+        content: Raw content (string, dict, or list)
+        
+    Returns:
+        Delimited string for LLM consumption
+    """
+    if isinstance(content, (dict, list)):
+        text = json.dumps(content, indent=2, ensure_ascii=False)
+    else:
+        text = str(content)
+    
+    return f"{START_DELIMITER}\n{text}\n{END_DELIMITER}"
+
+
+def unwrap_trusted_content(delimited: str) -> str:
+    """Extract content from delimiters (for testing/debugging).
+    
+    Args:
+        delimited: Content wrapped in delimiters
+        
+    Returns:
+        Raw content string
+    """
+    lines = delimited.split('\n')
+    if lines[0] == START_DELIMITER and lines[-1] == END_DELIMITER:
+        return '\n'.join(lines[1:-1])
+    return delimited

backend/packages/harness/deerflow/security/html_cleaner.py

@@ -0,0 +1,63 @@
+"""HTML-to-text extraction with security-focused stripping."""
+
+from html.parser import HTMLParser
+from typing import Optional
+
+
+class SecureTextExtractor(HTMLParser):
+    """Extract visible text while stripping potentially dangerous elements.
+    
+    Based on OpenClaw's fetch.sh implementation.
+    """
+    
+    DANGEROUS_TAGS = {
+        'script', 'style', 'noscript', 
+        'header', 'footer', 'nav', 'aside',
+        'iframe', 'object', 'embed', 'form',
+    }
+    
+    def __init__(self):
+        super().__init__()
+        self.text = []
+        self.skip_depth = 0
+    
+    def handle_starttag(self, tag, attrs):
+        if tag in self.DANGEROUS_TAGS:
+            self.skip_depth += 1
+    
+    def handle_endtag(self, tag):
+        if tag in self.DANGEROUS_TAGS and self.skip_depth > 0:
+            self.skip_depth -= 1
+    
+    def handle_data(self, data):
+        if self.skip_depth == 0:
+            self.text.append(data)
+    
+    def get_text(self) -> str:
+        return ' '.join(self.text)
+
+
+def extract_secure_text(html: str, max_chars: Optional[int] = None) -> str:
+    """Extract clean text from HTML.
+    
+    Args:
+        html: Raw HTML content
+        max_chars: Optional maximum length
+        
+    Returns:
+        Clean text without dangerous elements
+    """
+    extractor = SecureTextExtractor()
+    extractor.feed(html)
+    text = extractor.get_text()
+    
+    # Collapse whitespace
+    import re
+    text = re.sub(r'[ \t]+', ' ', text)
+    text = re.sub(r'\n{3,}', '\n\n', text)
+    text = text.strip()
+    
+    if max_chars and len(text) > max_chars:
+        text = text[:max_chars-3] + '...'
+    
+    return text

backend/packages/harness/deerflow/security/sanitizer.py

@@ -0,0 +1,94 @@
+"""Prompt injection hardening sanitizer based on OpenClaw patterns."""
+
+import re
+import unicodedata
+from typing import Optional
+
+
+class PromptInjectionSanitizer:
+    """Sanitizes external content for safe LLM consumption."""
+    
+    # Zero-width and invisible characters (OpenClaw pattern)
+    INVISIBLE_CHARS = [
+        '\u200b', '\u200c', '\u200d', '\u200e', '\u200f',  # Zero-width spaces
+        '\u2060', '\u2061', '\u2062', '\u2063', '\u2064',  # Word joiners
+        '\ufeff', '\ufffe',                                  # BOM
+        '\u00ad',                                           # Soft hyphen
+        '\u034f',                                           # Combining grapheme
+        '\u061c',                                           # Arabic letter mark
+        '\u115f', '\u1160',                                  # Hangul fillers
+        '\u17b4', '\u17b5',                                  # Khmer vowels
+        '\u180e',                                           # Mongolian separator
+        '\u3164',                                           # Hangul filler
+        '\uffa0',                                           # Halfwidth Hangul
+    ]
+    
+    def sanitize(self, text: str, max_length: Optional[int] = None) -> str:
+        """Apply all sanitization layers.
+        
+        Args:
+            text: Raw text to sanitize
+            max_length: Optional maximum length (with ellipsis)
+            
+        Returns:
+            Sanitized text safe for LLM prompts
+        """
+        if not text:
+            return ''
+        
+        # Layer 1: Remove invisible/zero-width characters
+        text = self._remove_invisible(text)
+        
+        # Layer 2: Remove control characters (except \n, \t)
+        text = self._remove_control_chars(text)
+        
+        # Layer 3: Remove symbols (So, Sk categories)
+        text = self._remove_symbols(text)
+        
+        # Layer 4: Normalize Unicode (NFC)
+        text = unicodedata.normalize('NFC', text)
+        
+        # Layer 5: Remove Private Use Area
+        text = self._remove_pua(text)
+        
+        # Layer 6: Remove tag characters
+        text = self._remove_tag_chars(text)
+        
+        # Layer 7: Collapse horizontal whitespace; preserve \n and \t so that
+        # list/table structure from web pages survives. Also collapse runs of
+        # 3+ blank lines down to a single blank line.
+        text = re.sub(r"[ \u00a0\u2000-\u200a\u202f\u205f\u3000]+", " ", text)
+        text = re.sub(r"\n{3,}", "\n\n", text)
+        text = text.strip()
+        
+        # Layer 8: Length limiting
+        if max_length and len(text) > max_length:
+            text = text[:max_length-3] + '...'
+        
+        return text
+    
+    def _remove_invisible(self, text: str) -> str:
+        for char in self.INVISIBLE_CHARS:
+            text = text.replace(char, '')
+        return text
+    
+    def _remove_control_chars(self, text: str) -> str:
+        return ''.join(c for c in text 
+                      if unicodedata.category(c) != 'Cc' or c in '\n\t')
+    
+    def _remove_symbols(self, text: str) -> str:
+        return ''.join(c for c in text 
+                      if unicodedata.category(c) not in ('So', 'Sk'))
+    
+    def _remove_pua(self, text: str) -> str:
+        return ''.join(c for c in text 
+                      if not (0xE000 <= ord(c) <= 0xF8FF 
+                             or 0xF0000 <= ord(c) <= 0x10FFFF))
+    
+    def _remove_tag_chars(self, text: str) -> str:
+        return ''.join(c for c in text 
+                      if not (0xE0000 <= ord(c) <= 0xE007F))
+
+
+# Global instance
+sanitizer = PromptInjectionSanitizer()