Security review fixes

python/obsidian_rag/security.py

@@ -64,6 +64,19 @@ HTML_TAG_RE = re.compile(r"<[^>]+>")
 CODE_BLOCK_RE = re.compile(r"```[\s\S]*?```", re.MULTILINE)
 MULTI_WHITESPACE_RE = re.compile(r"\s+")
 MAX_CHUNK_LEN = 2000
+INJECTION_PATTERNS = [
+    r"\x00",  # Null bytes
+    r"\x1a",  # EOF character
+    r"--\s",  # SQL comment
+    r"/\*[\s\S]*?\*/",  # SQL comment
+    r"';",  # SQL injection
+    r"\b(DROP|DELETE|INSERT|UPDATE|SELECT)\b",  # SQL keywords
+    r"<script[^>]*>.*?</script>",  # XSS
+    r"javascript:",  # JS injection
+    r"\b(eval|exec|spawn|fork|system)\b",  # Code execution
+]
+
+MAX_QUERY_LENGTH = 1000
 
 
 def sanitize_text(raw: str) -> str:
@@ -86,6 +99,25 @@ def sanitize_text(raw: str) -> str:
     if len(text) > MAX_CHUNK_LEN:
         text = text[:MAX_CHUNK_LEN]
     return text
+    """Sanitize raw vault content before embedding.
+
+    - Strip HTML tags (prevent XSS)
+    - Remove fenced code blocks
+    - Normalize whitespace
+    - Cap length at MAX_CHUNK_LEN chars
+    """
+    # Remove fenced code blocks
+    text = CODE_BLOCK_RE.sub(" ", raw)
+    # Strip HTML tags
+    text = HTML_TAG_RE.sub("", text)
+    # Remove leading/trailing whitespace
+    text = text.strip()
+    # Normalize internal whitespace
+    text = MULTI_WHITESPACE_RE.sub(" ", text)
+    # Cap length
+    if len(text) > MAX_CHUNK_LEN:
+        text = text[:MAX_CHUNK_LEN]
+    return text
 
 
 # ----------------------------------------------------------------------
@@ -93,6 +125,26 @@ def sanitize_text(raw: str) -> str:
 # ----------------------------------------------------------------------
 
 
+def sanitize_query(query: str) -> str:
+    """Sanitize search query to prevent prompt injection.
+    
+    - Remove injection patterns
+    - Normalize whitespace
+    - Limit length
+    """
+    # Remove injection patterns
+    for pattern in INJECTION_PATTERNS:
+        query = re.sub(pattern, " ", query, flags=re.IGNORECASE)
+    
+    # Normalize whitespace
+    query = MULTI_WHITESPACE_RE.sub(" ", query.strip())
+    
+    # Limit length
+    if len(query) > MAX_QUERY_LENGTH:
+        query = query[:MAX_QUERY_LENGTH]
+    
+    return query
+
 def detect_sensitive(
     text: str,
     sensitive_sections: list[str],