fix: keep SSRF DNS resolver on http(s)-proxy crawler paths

Commit 134ab54 dropped the safe DNS resolver for any configured proxy, but
that guard is only pointless for SOCKS proxies (where the proxy resolves the
target). On an http(s):// proxy reqwest still resolves the target locally, so
a hostname resolving to a private IP would be reachable. Narrow the exemption
to SOCKS-only via should_attach_safe_resolver.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

backend/src/crawler/safety.rs

@@ -289,6 +289,40 @@ pub fn safe_dns_resolver() -> Arc<SafeResolver> {
     Arc::new(SafeResolver)
 }
 
+/// Whether the DNS-rebinding [`SafeResolver`] should be attached to a crawler
+/// reqwest client given the configured proxy (if any).
+///
+/// The resolver only guards targets that *reqwest itself* resolves:
+/// - **No proxy** (direct): reqwest resolves the target — attach.
+/// - **`http(s)://` proxy**: reqwest still resolves the target host locally and
+///   issues a `CONNECT`, so a hostname resolving to a private IP must be
+///   refused — attach.
+/// - **`socks5://` / `socks5h://` / `socks4://` (Tor)**: the *proxy* resolves
+///   the target; reqwest only ever resolves the proxy's own host, which
+///   legitimately lives on a private Docker IP (e.g. `tor` → 172.x). Attaching
+///   the resolver there rejects every fetch for zero security gain (a SOCKS
+///   proxy can't route into internal ranges anyway) — do **not** attach.
+///
+/// This narrows commit 134ab54, which dropped the resolver for *any* proxy, back
+/// to SOCKS-only so the http(s)-proxy path keeps its DNS-rebinding guard.
+pub fn should_attach_safe_resolver(proxy: Option<&str>) -> bool {
+    match proxy {
+        None => true,
+        Some(p) => !is_socks_proxy(p),
+    }
+}
+
+/// True when `proxy`'s scheme is a SOCKS variant (`socks4`, `socks5`,
+/// `socks5h`). A scheme-less value (reqwest treats it as HTTP) is not SOCKS.
+fn is_socks_proxy(proxy: &str) -> bool {
+    proxy
+        .split_once("://")
+        .map(|(scheme, _)| scheme)
+        .unwrap_or("")
+        .to_ascii_lowercase()
+        .starts_with("socks")
+}
+
 #[derive(Debug, thiserror::Error, PartialEq, Eq)]
 pub enum UrlSafetyError {
     #[error("URL is not parseable")]
@@ -743,6 +777,24 @@ mod tests {
         assert!(err.to_string().contains("rebind.attacker"));
     }
 
+    #[test]
+    fn safe_resolver_attaches_except_for_socks_proxies() {
+        // Direct + http(s) proxies: reqwest resolves the target, so the
+        // DNS-rebinding guard must be attached.
+        assert!(should_attach_safe_resolver(None));
+        assert!(should_attach_safe_resolver(Some("http://proxy.internal:8080")));
+        assert!(should_attach_safe_resolver(Some("https://proxy.internal:8080")));
+        assert!(should_attach_safe_resolver(Some("HTTP://Proxy:8080")));
+        // A scheme-less proxy is treated as HTTP by reqwest — keep the guard.
+        assert!(should_attach_safe_resolver(Some("proxy.internal:8080")));
+        // SOCKS variants (incl. Tor): the proxy resolves, so attaching the
+        // resolver would reject every fetch for zero gain.
+        assert!(!should_attach_safe_resolver(Some("socks5://tor:9050")));
+        assert!(!should_attach_safe_resolver(Some("socks5h://tor:9050")));
+        assert!(!should_attach_safe_resolver(Some("socks4://x:1080")));
+        assert!(!should_attach_safe_resolver(Some("SOCKS5://Tor:9050")));
+    }
+
     #[test]
     fn safe_url_blocks_non_http_schemes() {
         let allow = allow_just("anywhere");