fix: SSRF in /api/parse-url via DNS bypass and redirects (#878)

* fix: resolve DNS before SSRF check and block redirects in parse-url

isPrivateUrl() did string-only hostname matching and never resolved DNS,
so a public-looking name that maps to an internal IP (e.g.
127-0-0-1.sslip.io -> 127.0.0.1) passed the check while fetch/extract
later resolved it and reached internal services (GHSA-wqcv-5qvx-vx75).

- isPrivateUrl is now async: it keeps the fast string/literal-IP path,
  then resolves the hostname via DNS and rejects if any address is private.
- parse-url now fetches the page itself with redirect: "error" and parses
  via extractFromHtml(), since article-extractor follows redirects
  internally and drops a redirect option, which allowed a public URL to
  302 to an internal host.
- Update validate-model call site to await; add regression tests.

* fix: preserve charset detection and block CGNAT range in parse-url SSRF fix

Follow-up to the multi-reviewer review of the SSRF fix:

- Restore charset handling lost when switching from extract() to
  response.text(): non-UTF-8 pages (Shift_JIS/GBK/EUC/Big5, common on CJK
  sites this project targets) decoded as mojibake. Now read the body as
  bytes, detect charset from Content-Type / <meta charset>, and decode
  with TextDecoder before extractFromHtml.
- Wrap extractFromHtml in try/catch: it throws (not returns null) on
  empty/non-HTML bodies, which previously surfaced as a 500 instead of the
  intended 400.
- Add 100.64.0.0/10 (RFC 6598 CGNAT) to isPrivateIp; it is routable inside
  some cloud internal networks and was a residual SSRF target.
- Add tests for CGNAT, its boundaries, 0.0.0.0, and DNS-resolved IPv6.

tests/unit/ssrf-protection.test.ts

@@ -1,21 +1,79 @@
-import { describe, expect, it } from "vitest"
+import { beforeEach, describe, expect, it, vi } from "vitest"
 import { isPrivateUrl } from "@/lib/ssrf-protection"
 
+// Mock DNS so tests are deterministic and never hit the network.
+const lookupMock = vi.hoisted(() => vi.fn())
+vi.mock("node:dns/promises", () => ({
+    default: { lookup: lookupMock },
+    lookup: lookupMock,
+}))
+
 describe("isPrivateUrl", () => {
-    it("blocks private IPv6 URLs", () => {
-        expect(isPrivateUrl("http://[::1]/")).toBe(true)
-        expect(isPrivateUrl("http://[0:0:0:0:0:0:0:1]/")).toBe(true)
-        expect(isPrivateUrl("http://[::]/")).toBe(true)
-        expect(isPrivateUrl("http://[::ffff:127.0.0.1]/")).toBe(true)
-        expect(isPrivateUrl("http://[fc00::1]/")).toBe(true)
-        expect(isPrivateUrl("http://[fd12:3456:789a::1]/")).toBe(true)
-        expect(isPrivateUrl("http://[fe80::1]/")).toBe(true)
-        expect(isPrivateUrl("http://[fe9f::1]/")).toBe(true)
-        expect(isPrivateUrl("http://[febf::1]/")).toBe(true)
+    beforeEach(() => {
+        lookupMock.mockReset()
     })
 
-    it("allows public URLs", () => {
-        expect(isPrivateUrl("https://example.com/article")).toBe(false)
-        expect(isPrivateUrl("https://fc00.example.com/article")).toBe(false)
+    it("blocks private IPv6 URLs (string-only fast path, no DNS)", async () => {
+        expect(await isPrivateUrl("http://[::1]/")).toBe(true)
+        expect(await isPrivateUrl("http://[0:0:0:0:0:0:0:1]/")).toBe(true)
+        expect(await isPrivateUrl("http://[::]/")).toBe(true)
+        expect(await isPrivateUrl("http://[::ffff:127.0.0.1]/")).toBe(true)
+        expect(await isPrivateUrl("http://[fc00::1]/")).toBe(true)
+        expect(await isPrivateUrl("http://[fd12:3456:789a::1]/")).toBe(true)
+        expect(await isPrivateUrl("http://[fe80::1]/")).toBe(true)
+        expect(await isPrivateUrl("http://[fe9f::1]/")).toBe(true)
+        expect(await isPrivateUrl("http://[febf::1]/")).toBe(true)
+        expect(lookupMock).not.toHaveBeenCalled()
+    })
+
+    it("blocks literal private IPv4 without DNS", async () => {
+        expect(await isPrivateUrl("http://127.0.0.1/")).toBe(true)
+        expect(await isPrivateUrl("http://10.0.0.5/")).toBe(true)
+        expect(await isPrivateUrl("http://192.168.1.1/")).toBe(true)
+        expect(await isPrivateUrl("http://169.254.169.254/")).toBe(true)
+        expect(await isPrivateUrl("http://0.0.0.0/")).toBe(true)
+        // 100.64.0.0/10 CGNAT (RFC 6598), routable in some cloud internal nets
+        expect(await isPrivateUrl("http://100.64.0.1/")).toBe(true)
+        expect(await isPrivateUrl("http://100.127.255.255/")).toBe(true)
+        expect(lookupMock).not.toHaveBeenCalled()
+    })
+
+    it("treats CGNAT boundaries correctly", async () => {
+        // 100.63.x and 100.128.x are outside 100.64.0.0/10 → public
+        lookupMock.mockResolvedValue([{ address: "100.63.255.255", family: 4 }])
+        expect(await isPrivateUrl("http://just-below.example/")).toBe(false)
+        lookupMock.mockResolvedValue([{ address: "100.128.0.1", family: 4 }])
+        expect(await isPrivateUrl("http://just-above.example/")).toBe(false)
+    })
+
+    it("blocks a hostname that resolves to a private IPv6 address", async () => {
+        lookupMock.mockResolvedValue([{ address: "fd00::1", family: 6 }])
+        expect(await isPrivateUrl("http://v6.example.com/")).toBe(true)
+    })
+
+    it("allows public URLs that resolve to public IPs", async () => {
+        lookupMock.mockResolvedValue([{ address: "93.184.216.34", family: 4 }])
+        expect(await isPrivateUrl("https://example.com/article")).toBe(false)
+    })
+
+    it("blocks public-looking hostnames that resolve to a private IP (DNS-rebinding-style bypass)", async () => {
+        // e.g. 127-0-0-1.sslip.io resolves to 127.0.0.1
+        lookupMock.mockResolvedValue([{ address: "127.0.0.1", family: 4 }])
+        expect(await isPrivateUrl("http://127-0-0-1.sslip.io/")).toBe(true)
+    })
+
+    it("blocks when any resolved address is private", async () => {
+        lookupMock.mockResolvedValue([
+            { address: "93.184.216.34", family: 4 },
+            { address: "10.1.2.3", family: 4 },
+        ])
+        expect(await isPrivateUrl("http://mixed.example.com/")).toBe(true)
+    })
+
+    it("blocks when DNS resolution fails", async () => {
+        lookupMock.mockRejectedValue(new Error("ENOTFOUND"))
+        expect(await isPrivateUrl("http://does-not-resolve.example/")).toBe(
+            true,
+        )
     })
 })