2.4Output Validation Framework

# output_sanitizer.py
import re
import html
from urllib.parse import urlparse

class LLMOutputSanitizer:
    """Sanitize LLM output before use in downstream operations."""

    @staticmethod
    def for_html(text: str) -> str:
        """Sanitize for HTML rendering."""
        sanitized = html.escape(text)
        # Also strip javascript: URLs
        sanitized = re.sub(r'javascript:', '', sanitized, flags=re.IGNORECASE)
        return sanitized

    @staticmethod
    def for_sql_value(text: str) -> str:
        """Sanitize for use as a SQL value (prefer parameterized queries)."""
        # This is a last resort -- always use parameterized queries instead
        return text.replace("'", "''").replace(";", "").replace("--", "")

    @staticmethod
    def for_filename(text: str) -> str:
        """Sanitize for use as a filesystem path."""
        # Remove path traversal and shell metacharacters
        sanitized = re.sub(r'[;|`$(){}\\]', '', text)
        sanitized = sanitized.replace("..", "")
        sanitized = sanitized.replace("/", "_")
        return sanitized

    @staticmethod
    def for_url(text: str) -> str:
        """Validate and sanitize URLs from LLM output."""
        parsed = urlparse(text)
        if parsed.scheme not in ("http", "https"):
            raise ValueError(f"Invalid URL scheme: {parsed.scheme}")
        if parsed.hostname and parsed.hostname.endswith(".internal"):
            raise ValueError(f"Internal URL not allowed: {text}")
        return text