bitfennec
1059be1b62
- Rust core engine with HTTP ingestion gateway, hybrid search, and white-box resume matching - Python edge collectors supporting declarative TOML and specialized adapters - PostgreSQL schema migrations with pgvector embedding support - Hardened security controls: strict CSP, terminal sanitization, and input boundary validation - Multi-service container orchestration with dedicated non-root execution
36 lines
959 B
Python
36 lines
959 B
Python
import ipaddress
|
|
from urllib.parse import urlsplit
|
|
|
|
|
|
def is_safe_url(
|
|
url: str,
|
|
allowed_domains: list[str] | None = None,
|
|
default_host: str = "",
|
|
) -> bool:
|
|
try:
|
|
parts = urlsplit(url)
|
|
if parts.scheme not in ("http", "https"):
|
|
return False
|
|
|
|
host = (parts.hostname or "").lower()
|
|
if not host or host in ("localhost", "127.0.0.1", "::1"):
|
|
return False
|
|
|
|
try:
|
|
ip = ipaddress.ip_address(host)
|
|
if ip.is_private or ip.is_loopback or ip.is_link_local or ip.is_reserved:
|
|
return False
|
|
except ValueError:
|
|
pass
|
|
|
|
domains = [d.lower() for d in (allowed_domains or []) if d]
|
|
if not domains and default_host:
|
|
domains = [default_host.lower()]
|
|
|
|
if not domains:
|
|
return True
|
|
|
|
return any(host == d or host.endswith("." + d) for d in domains)
|
|
except Exception:
|
|
return False
|