fix(portal-clis): reject foreign detail URLs in Jobbank and Jobnet (#672)

* fix(portal-clis): validate Jobbank and Jobnet detail URL hosts

* fix(portal-clis): preserve scheme-less portal detail URLs

Normalize host-like input with HTTPS before validating the portal host. Cover apex, www, mobile, uppercase and legacy routes while rejecting foreign or deceptive hosts and query-only posting paths.

Thanks to MadsLorentzen for finding the compatibility regression in #672.

* changelog: place the #672 entry under [Unreleased]

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

.agents/skills/jobbank-search/cli/src/helpers.ts

@@ -162,7 +162,18 @@ export function parseRssDescription(desc: string): ParsedDescription {
 export function normalizeJobId(input: string): string | null {
   const trimmed = input.trim()
   if (/^\d+$/.test(trimmed)) return trimmed
-  const match = trimmed.match(/\/job\/(\d+)(?:\/|$|\?|#)/)
+  let url: URL
+  try {
+    const hostLike = /^[a-z0-9.-]+\.[a-z]{2,}(\/|$)/i.test(trimmed)
+    url = new URL(hostLike ? `https://${trimmed}` : trimmed)
+  } catch {
+    return null
+  }
+  if (url.protocol !== "http:" && url.protocol !== "https:") return null
+  if (url.hostname !== "jobbank.dk" && !url.hostname.endsWith(".jobbank.dk")) return null
+  // A matching path on a different site is not a Jobbank posting. Read only
+  // the parsed pathname, so a job URL embedded in a query is not an ID either.
+  const match = url.pathname.match(/^\/job\/(\d+)(?:\/|$)/)
   return match ? match[1] : null
 }
 

.agents/skills/jobbank-search/cli/tests/detail-url-normalization.test.ts

@@ -3,6 +3,42 @@ import { normalizeJobId } from "../src/helpers.js"
 import { runCLI } from "./helpers.js"
 
 describe("jobbank-search normalizeJobId", () => {
+  test("accepts portal URLs without a scheme", () => {
+    for (const host of ["jobbank.dk", "www.jobbank.dk", "m.jobbank.dk", "JOBBANK.DK"]) {
+      expect(normalizeJobId(` ${host}/job/3117065/company/role?ref=search#apply `)).toBe("3117065")
+    }
+  })
+
+  test("rejects foreign hosts, non-web schemes and job paths only in a query", () => {
+    for (const value of [
+      "https://example.com/job/304212/",
+      "https://jobbank.dk.example.com/job/304212/",
+      "ftp://jobbank.dk/job/304212/",
+      "https://jobbank.dk/?next=/job/304212/",
+      "example.com/job/304212/",
+      "jobbank.dk.evil.io/job/304212/",
+      "jobbank.dk@evil.io/job/304212/",
+      "jobbank.dk/?next=/job/304212/",
+    ]) expect(normalizeJobId(value)).toBeNull()
+  })
+
+  test("accepts the portal's www host and HTTP links", () => {
+    expect(normalizeJobId("http://www.jobbank.dk/job/304212/")).toBe("304212")
+  })
+
+  test("CLI rejects another site's matching job path before any fetch", async () => {
+    const proc = Bun.spawn([
+      process.execPath, "--preload", `${import.meta.dir}/reject-network.ts`,
+      `${import.meta.dir}/../src/cli.ts`, "detail", "https://example.com/job/304212/",
+    ], { stdout: "pipe", stderr: "pipe" })
+    const [stdout, stderr, code] = await Promise.all([
+      new Response(proc.stdout).text(), new Response(proc.stderr).text(), proc.exited,
+    ])
+    expect(code).toBe(1)
+    expect(stdout).toBe("")
+    expect(JSON.parse(stderr).code).toBe("BAD_ID")
+  })
+
   test("accepts bare numeric ID", () => {
     expect(normalizeJobId("304212")).toBe("304212")
     expect(normalizeJobId("  12345  ")).toBe("12345")

.agents/skills/jobbank-search/cli/tests/reject-network.ts

@@ -0,0 +1,3 @@
+globalThis.fetch = Object.assign(async () => {
+  throw new Error("unexpected network request for an invalid detail URL")
+}, { preconnect() {} })

.agents/skills/jobnet-search/cli/src/helpers.ts

@@ -60,7 +60,18 @@ export function normalizeJobId(input: string): string | null {
   const trimmed = input.trim()
   if (!trimmed) return null
   if (/^[a-zA-Z0-9_-]+$/.test(trimmed)) return trimmed
-  const match = trimmed.match(/(?:\/find-job\/|\/JobAdDetails\/|\/Details\/)(?:detaljer\/)?([a-zA-Z0-9_-]+)(?:\/|$|\?|#)/i)
+  let url: URL
+  try {
+    const hostLike = /^[a-z0-9.-]+\.[a-z]{2,}(\/|$)/i.test(trimmed)
+    url = new URL(hostLike ? `https://${trimmed}` : trimmed)
+  } catch {
+    return null
+  }
+  if (url.protocol !== "http:" && url.protocol !== "https:") return null
+  if (url.hostname !== "jobnet.dk" && !url.hostname.endsWith(".jobnet.dk")) return null
+  // Otherwise an unrelated site's matching path silently selects a Jobnet ad.
+  // Keep legacy routes, but never interpret a query or fragment as a job path.
+  const match = url.pathname.match(/(?:\/find-job\/|\/JobAdDetails\/|\/Details\/)(?:detaljer\/)?([a-zA-Z0-9_-]+)(?:\/|$)/i)
   if (match) return match[1]
   return null
 }

.agents/skills/jobnet-search/cli/tests/detail-url-normalization.test.ts

@@ -3,6 +3,44 @@ import { normalizeJobId } from "../src/helpers.js"
 import { runCLI } from "./helpers.js"
 
 describe("jobnet-search normalizeJobId", () => {
+  test("accepts portal URLs without a scheme", () => {
+    const id = "12345678-1234-1234-1234-123456789abc"
+    for (const host of ["jobnet.dk", "www.jobnet.dk", "m.jobnet.dk", "JOBNET.DK"]) {
+      expect(normalizeJobId(` ${host}/find-job/${id}?ref=search#apply `)).toBe(id)
+    }
+    expect(normalizeJobId(`job.jobnet.dk/CV/FindWork/Details/${id}`)).toBe(id)
+  })
+
+  test("rejects foreign hosts, non-web schemes and job paths only in a query", () => {
+    for (const value of [
+      "https://example.com/find-job/6123456/",
+      "https://jobnet.dk.example.com/find-job/6123456/",
+      "ftp://jobnet.dk/find-job/6123456/",
+      "https://jobnet.dk/?next=/find-job/6123456/",
+      "example.com/find-job/6123456/",
+      "jobnet.dk.evil.io/find-job/6123456/",
+      "jobnet.dk@evil.io/find-job/6123456/",
+      "jobnet.dk/?next=/find-job/6123456/",
+    ]) expect(normalizeJobId(value)).toBeNull()
+  })
+
+  test("accepts the portal's www host and HTTP links", () => {
+    expect(normalizeJobId("http://www.jobnet.dk/find-job/6123456/")).toBe("6123456")
+  })
+
+  test("CLI rejects another site's matching job path before any fetch", async () => {
+    const proc = Bun.spawn([
+      process.execPath, "--preload", `${import.meta.dir}/reject-network.ts`,
+      `${import.meta.dir}/../src/cli.ts`, "detail", "https://example.com/find-job/6123456/",
+    ], { stdout: "pipe", stderr: "pipe" })
+    const [stdout, stderr, code] = await Promise.all([
+      new Response(proc.stdout).text(), new Response(proc.stderr).text(), proc.exited,
+    ])
+    expect(code).toBe(1)
+    expect(stdout).toBe("")
+    expect(JSON.parse(stderr).code).toBe("BAD_ID")
+  })
+
   test("accepts bare numeric ID", () => {
     expect(normalizeJobId("6123456")).toBe("6123456")
     expect(normalizeJobId("  6123456  ")).toBe("6123456")

.agents/skills/jobnet-search/cli/tests/reject-network.ts

@@ -0,0 +1,3 @@
+globalThis.fetch = Object.assign(async () => {
+  throw new Error("unexpected network request for an invalid detail URL")
+}, { preconnect() {} })