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.
This commit is contained in:
dayuan.jiang
2026-06-27 18:03:28 +09:00
parent 5c884766a8
commit 73862f6108
4 changed files with 182 additions and 109 deletions

View File

@@ -2,80 +2,107 @@
* SSRF (Server-Side Request Forgery) protection utilities
*/
import { lookup } from "node:dns/promises"
/**
* Check if URL points to private/internal network
* Blocks: localhost, private IPs, link-local, AWS metadata service
* Check if an IP address (IPv4 or IPv6) belongs to a private/internal range.
* Works for both user-supplied literal IPs and DNS-resolved addresses.
*/
export function isPrivateUrl(urlString: string): boolean {
function isPrivateIp(ip: string): boolean {
const addr = ip.toLowerCase().replace(/^\[|\]$/g, "")
// IPv6
if (addr.includes(":")) {
if (addr === "::1" || addr === "::") return true
// unique-local (fc00::/7) and IPv4-mapped (::ffff:0:0/96)
if (
addr.startsWith("fc") ||
addr.startsWith("fd") ||
addr.startsWith("::ffff:")
) {
return true
}
// link-local (fe80::/10)
const linkLocal = addr.match(/^fe([0-9a-f]{2}):/)
if (linkLocal) {
const high = parseInt(linkLocal[1], 16)
if (high >= 0x80 && high <= 0xbf) return true
}
return false
}
// IPv4
const ipv4Match = addr.match(/^(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/)
if (ipv4Match) {
const [, a, b] = ipv4Match.map(Number)
if (a === 10) return true // 10.0.0.0/8
if (a === 172 && b >= 16 && b <= 31) return true // 172.16.0.0/12
if (a === 192 && b === 168) return true // 192.168.0.0/16
if (a === 169 && b === 254) return true // 169.254.0.0/16 (link-local)
if (a === 127) return true // 127.0.0.0/8 (loopback)
if (a === 0) return true // 0.0.0.0/8
}
return false
}
/**
* String-only check against well-known private hostnames and literal IPs.
* Fast path that avoids a DNS lookup for obvious cases.
*/
function isPrivateHostname(hostname: string): boolean {
const host = hostname
.toLowerCase()
.replace(/^\[|\]$/g, "")
.replace(/\.$/, "")
if (
host === "localhost" ||
host === "127.0.0.1" ||
host === "::1" ||
host === "::"
) {
return true
}
if (host === "169.254.169.254" || host === "metadata.google.internal") {
return true
}
if (
host.endsWith(".local") ||
host.endsWith(".internal") ||
host.endsWith(".localhost")
) {
return true
}
// Literal IP supplied directly in the URL
return isPrivateIp(host)
}
/**
* Check if URL points to private/internal network.
* Blocks: localhost, private IPs, link-local, AWS metadata service.
*
* Resolves the hostname via DNS and validates every returned address, so
* public-looking names that map to internal IPs (e.g. "127-0-0-1.sslip.io")
* are caught even though they pass the string-only check.
*/
export async function isPrivateUrl(urlString: string): Promise<boolean> {
try {
const url = new URL(urlString)
// Strip a trailing dot so FQDN forms like "localhost." (which still
// resolve to 127.0.0.1) cannot bypass the equality checks below.
const hostname = url.hostname
.toLowerCase()
.replace(/^\[|\]$/g, "")
.replace(/\.$/, "")
// Block localhost
if (
hostname === "localhost" ||
hostname === "127.0.0.1" ||
hostname === "::1" ||
hostname === "::"
) {
return true
}
// Fast path: obvious string matches and literal IPs.
if (isPrivateHostname(hostname)) return true
// Block IPv6 unique-local (fc00::/7), link-local (fe80::/10),
// and IPv4-mapped (::ffff:0:0/96) hosts.
if (hostname.includes(":")) {
if (
hostname.startsWith("fc") ||
hostname.startsWith("fd") ||
hostname.startsWith("::ffff:")
) {
return true
}
const linkLocal = hostname.match(/^fe([0-9a-f]{2}):/)
if (linkLocal) {
const high = parseInt(linkLocal[1], 16)
if (high >= 0x80 && high <= 0xbf) return true
}
}
// Block AWS/cloud metadata endpoints
if (
hostname === "169.254.169.254" ||
hostname === "metadata.google.internal"
) {
return true
}
// Check for private IPv4 ranges
const ipv4Match = hostname.match(
/^(\d{1,3})\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/,
)
if (ipv4Match) {
const [, a, b] = ipv4Match.map(Number)
if (a === 10) return true // 10.0.0.0/8
if (a === 172 && b >= 16 && b <= 31) return true // 172.16.0.0/12
if (a === 192 && b === 168) return true // 192.168.0.0/16
if (a === 169 && b === 254) return true // 169.254.0.0/16 (link-local)
if (a === 127) return true // 127.0.0.0/8 (loopback)
}
// Block common internal hostnames
if (
hostname.endsWith(".local") ||
hostname.endsWith(".internal") ||
hostname.endsWith(".localhost")
) {
return true
}
return false
// Resolve DNS and reject if any address is private.
const stripped = hostname.replace(/^\[|\]$/g, "").replace(/\.$/, "")
const addresses = await lookup(stripped, { all: true })
return addresses.some(({ address }) => isPrivateIp(address))
} catch {
return true // Invalid URL - block it
return true // Invalid URL or DNS failure - block it
}
}