fix(freehire-search): reject detail URLs on other hosts instead of asking the API for their last segment (#622) (#623)

* fix(freehire-search): reject detail URLs on other hosts instead of asking the API for their last segment

normalizeSlug took the segment after "/jobs/" from ANY string, so a
Greenhouse apply link - which is what a freehire search result's own url
field carries - was reduced to its last path segment and detail
requested /api/v1/jobs/1, then reported NOT_FOUND for a URL that was
never a freehire posting. Every other portal CLI rejects an off-host
detail URL with BAD_ID (#447, #430, #499); freehire was the last one
trusting the path.

Parse URLs for real: freehire.me (apex or any subdomain, scheme optional)
or the host of FREEHIRE_API_URL for a self-hosted instance, plus a
/jobs/<slug> path, yields the slug; other hosts, look-alike and userinfo
hosts, and non-job freehire pages exit 1 with BAD_ID before any request.
Bare slugs are unchanged.

Five new normalizeSlug cases and a handler-level test that pastes the
search fixture's own apply URL into detail with fetch stubbed; the
off-host cases fail on master.

* changelog: place the #623 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/freehire-search/SKILL.md

@@ -124,7 +124,7 @@ bun run .agents/skills/freehire-search/cli/src/cli.ts detail <slug|url> [--forma
 ```
 
 `slug` is the `id` from a `search` result (e.g. `golang-zensar-2bxu6dxm`). You may
-also pass a full `https://freehire.me/jobs/<slug>` URL. Returns the full (HTML-stripped)
+also pass a full `https://freehire.me/jobs/<slug>` URL. A URL on any other host - including the employer apply link a search result's `url` field carries - is rejected with `BAD_ID` before any request. Returns the full (HTML-stripped)
 description, skills, region/country, and — when the posting is enriched — seniority,
 category, employment type, and salary. `salary` keeps its period when freehire records
 one (`INR 300000–300000/year`, `INR 12000/month`); compare pay only in one period.

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

@@ -246,12 +246,46 @@ export function cleanHtml(html: string | null | undefined): string | null {
   return text || null
 }
 
-/** Extract a freehire public slug from a bare slug or a /jobs/<slug> URL. */
+const FREEHIRE_HOST = /(^|\.)freehire\.me$/i
+
+/** True for freehire.me, any of its subdomains, or the configured self-hosted base URL's host. */
+function isFreehireHost(host: string): boolean {
+  if (FREEHIRE_HOST.test(host)) return true
+  try {
+    const self = new URL(baseUrl()).hostname.toLowerCase()
+    return host === self || host.endsWith(`.${self}`)
+  } catch {
+    return false
+  }
+}
+
+/**
+ * Extract a freehire public slug from a bare slug or a freehire `/jobs/<slug>` URL.
+ *
+ * A URL on any other host is rejected. The previous pattern took the segment
+ * after `/jobs/` from ANY string, so a Greenhouse apply link - which is what a
+ * freehire search result's own `url` field carries - was reduced to its last
+ * path segment and `detail` asked the API for a slug that never existed,
+ * reporting "job not found" for a URL that was never a freehire posting. URLs
+ * are parsed for real, so look-alike hosts (freehire.me.evil.io) and userinfo
+ * tricks (freehire.me@evil.io) fall on the reject side; FREEHIRE_API_URL's host
+ * is accepted for a self-hosted instance.
+ */
 export function normalizeSlug(input: string): string | null {
   const trimmed = input.trim()
   if (!trimmed) return null
-  const m = trimmed.match(/\/jobs\/([^/?#]+)/)
-  if (m) return m[1]
+  const hasScheme = /^https?:\/\//i.test(trimmed)
+  if (hasScheme || /^[a-z0-9.-]+\.[a-z]{2,}(\/|$)/i.test(trimmed)) {
+    let parsed: URL
+    try {
+      parsed = new URL(hasScheme ? trimmed : `https://${trimmed}`)
+    } catch {
+      return null
+    }
+    if (!isFreehireHost(parsed.hostname.toLowerCase())) return null
+    const m = parsed.pathname.match(/^\/jobs\/([a-z0-9][a-z0-9-]*)\/?$/i)
+    return m ? m[1] : null
+  }
   // A bare slug: lowercase alphanumerics and hyphens (no path/scheme).
   if (/^[a-z0-9][a-z0-9-]*$/i.test(trimmed)) return trimmed
   return null

.agents/skills/freehire-search/cli/tests/commands.test.ts

@@ -235,3 +235,20 @@ describe("runDetail (mocked fetch)", () => {
     expect(JSON.parse(err).code).toBe("NOT_FOUND");
   });
 });
+
+describe("detail input on the real handler path", () => {
+  test("a search result's own apply URL is rejected with BAD_ID before any request", async () => {
+    // Every freehire search result carries the employer's apply link in `url`
+    // (the fixture's is a Greenhouse board). Pasting it back into detail used
+    // to request /api/v1/jobs/1 and report NOT_FOUND for a URL that was never
+    // a freehire posting.
+    const mock = mockFetch(404, { error: "not found" });
+    const err = captureStderr();
+
+    const code = await runDetail({ id: job().url, format: "json" });
+
+    expect(code).toBe(1);
+    expect(mock.url()).toBe("");
+    expect(JSON.parse(err.get())).toMatchObject({ code: "BAD_ID" });
+  });
+});

.agents/skills/freehire-search/cli/tests/parsing.test.ts

@@ -147,4 +147,44 @@ describe("normalizeSlug", () => {
     expect(normalizeSlug("not a slug!")).toBeNull();
     expect(normalizeSlug("")).toBeNull();
   });
+  test("accepts subdomains, a scheme-less host, a trailing slash and a query string", () => {
+    expect(normalizeSlug("https://www.freehire.me/jobs/golang-zensar-2bxu6dxm/")).toBe("golang-zensar-2bxu6dxm");
+    expect(normalizeSlug("freehire.me/jobs/golang-zensar-2bxu6dxm?utm_source=x")).toBe("golang-zensar-2bxu6dxm");
+  });
+  test("rejects a /jobs/ URL on another host instead of asking the API for its last segment", () => {
+    // The search fixture's own `url` is a Greenhouse apply link; pasting it
+    // back into detail used to request /api/v1/jobs/1 and report NOT_FOUND.
+    expect(normalizeSlug("https://boards.greenhouse.io/acme/jobs/1")).toBeNull();
+    expect(normalizeSlug("https://jobs.lever.co/acme/jobs/abc")).toBeNull();
+  });
+  test("rejects look-alike and userinfo hosts", () => {
+    expect(normalizeSlug("https://freehire.me.evil.io/jobs/x")).toBeNull();
+    expect(normalizeSlug("https://notfreehire.me/jobs/x")).toBeNull();
+    expect(normalizeSlug("https://freehire.me@evil.io/jobs/x")).toBeNull();
+  });
+  test("rejects a freehire.me URL that is not a job page", () => {
+    expect(normalizeSlug("https://freehire.me/companies/acme")).toBeNull();
+    expect(normalizeSlug("https://freehire.me/jobs/")).toBeNull();
+  });
+  test("requires the path to be exactly /jobs/<slug>", () => {
+    // The slug is the whole path after /jobs/: a nested path, a prefix before
+    // /jobs/, or a slug with characters outside the slug alphabet is not a
+    // freehire job page, even on the right host.
+    expect(normalizeSlug("https://freehire.me/jobs/my-slug/apply")).toBeNull();
+    expect(normalizeSlug("https://freehire.me/en/jobs/my-slug")).toBeNull();
+    expect(normalizeSlug("https://freehire.me/jobs/my_slug")).toBeNull();
+    expect(normalizeSlug("https://freehire.me/jobs/my-slug#details")).toBe("my-slug");
+  });
+
+  test("accepts the self-hosted base URL's host", () => {
+    const saved = process.env.FREEHIRE_API_URL;
+    process.env.FREEHIRE_API_URL = "http://localhost:8080";
+    try {
+      expect(normalizeSlug("http://localhost:8080/jobs/my-slug")).toBe("my-slug");
+      expect(normalizeSlug("https://boards.greenhouse.io/acme/jobs/1")).toBeNull();
+    } finally {
+      if (saved === undefined) delete process.env.FREEHIRE_API_URL;
+      else process.env.FREEHIRE_API_URL = saved;
+    }
+  });
 });