Merge feature/dc-064-discover-adopt-fetcht: DC-070 caddycode config sanitization [glm-grade=A]

dashcaddy-api/__tests__/routes/caddycode-dc070.routes.test.js

@@ -0,0 +1,277 @@
+/**
+ * DC-070: Caddycode config sanitization — validate the structural config
+ * that flows into generateSiteBlock(), and confirm that the post-fix
+ * generation does NOT interpolate raw user input into Caddyfile text.
+ *
+ * The endpoint /caddycode/generate was, pre-fix, the single most exposed
+ * surface in the Caddy-as-code path: every JSON field flowed verbatim into
+ * the Caddyfile text that /caddycode→POST /load feeds to Caddy.
+ *
+ * Bug class under test:
+ *   1. CRLF / newline in `domain` → close the block and inject a new site
+ *   2. `"` (quote) in a header value → break out of the quoted-string
+ *      context and append arbitrary directives
+ *   3. `}` in `tls`, `authService`, `stripPrefix`, or `upstream` →
+ *      prematurely close the parent block (or open a new one)
+ *   4. `://` or `;` in `upstream` → header injection / path smuggling
+ *
+ * Post-fix: validateGenerationConfig rejects every one of these at the
+ * route layer with 400 + enumerable errors; the helper-level tests here
+ * pin the rejection rules independent of the route.
+ */
+
+const { __test } = require('../../routes/caddycode');
+const { validateGenerationConfig, escapeCaddyQuotedString, generateSiteBlock } = __test;
+
+const BASE_OK = {
+  domain: 'app.example.com',
+  upstream: 'localhost:8080',
+};
+
+function check(cond, msg) {
+  if (!cond) throw new Error('assertion failed: ' + msg);
+}
+
+describe('DC-070: caddycode config sanitization', () => {
+  describe('validateGenerationConfig — happy paths', () => {
+    test('minimal valid config passes', () => {
+      const r = validateGenerationConfig(BASE_OK);
+      check(r.valid === true, `expected valid=true, got errors=${JSON.stringify(r.errors)}`);
+      check(Array.isArray(r.errors) && r.errors.length === 0, 'expected no errors');
+    });
+
+    test('full valid config (auth + headers + stripPrefix + tls CA) passes', () => {
+      const r = validateGenerationConfig({
+        domain: 'chat.example.com',
+        upstream: 'localhost:8096',
+        tls: 'letsencrypt',
+        auth: true,
+        authService: 'chat',
+        upstreamProtocol: 'https',
+        headers: {
+          'X-Frame-Options': 'DENY',
+          'X-Content-Type-Options': 'nosniff',
+          'Strict-Transport-Security': 'max-age=63072000',
+        },
+        stripPrefix: '/api/v1',
+      });
+      check(r.valid === true, `expected valid, got errors=${JSON.stringify(r.errors)}`);
+    });
+
+    test('IPv6 bracket-form upstream accepted', () => {
+      const r = validateGenerationConfig({ domain: 'dns.example.com', upstream: '[::1]:5380' });
+      check(r.valid === true, `IPv6 bracket should pass: ${JSON.stringify(r.errors)}`);
+    });
+
+    test('bare host without :port rejected (DC-070 round 2)', () => {
+      // Round-1 polish: Caddy reverse_proxy requires an explicit :port
+      // segment. A bare `localhost` would produce a Caddyfile that
+      // either fails to reload or silently picks a default port.
+      const r = validateGenerationConfig({ domain: 'app.example.com', upstream: 'localhost' });
+      check(r.valid === false, `bare host should reject: ${JSON.stringify(r.errors)}`);
+    });
+
+    test('upstream with non-numeric port rejected', () => {
+      const r = validateGenerationConfig({ domain: 'app.example.com', upstream: 'localhost:abc' });
+      check(r.valid === false, `non-numeric port should reject: ${JSON.stringify(r.errors)}`);
+    });
+  });
+
+  describe('validateGenerationConfig — injection rejection', () => {
+    test('CRLF in domain rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, domain: 'evil.com\nnew.site.example.com {' });
+      check(r.valid === false, 'CRLF should reject');
+      check(r.errors.some((e) => /domain/.test(e)), `expected error to mention domain, got ${JSON.stringify(r.errors)}`);
+    });
+
+    test('brace in domain rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, domain: 'evil} malicious' });
+      check(r.valid === false, 'brace should reject');
+    });
+
+    test('"://" in upstream rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, upstream: 'http://evil.tld/x' });
+      check(r.valid === false, ':// should reject');
+    });
+
+    test('space + brace in upstream rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, upstream: 'localhost:8080 } evil {' });
+      check(r.valid === false, 'whitespace+brace in upstream should reject');
+    });
+
+    test('CRLF in header value rejected', () => {
+      const r = validateGenerationConfig({
+        ...BASE_OK,
+        headers: { 'X-Custom': 'innocent\r\nHost: evil.tld' },
+      });
+      check(r.valid === false, 'CRLF in header value should reject');
+      check(r.errors.some((e) => /CR or LF/i.test(e)), `expected CR/LF error: ${JSON.stringify(r.errors)}`);
+    });
+
+    test('bad header key charset rejected', () => {
+      const r = validateGenerationConfig({
+        ...BASE_OK,
+        headers: { 'X Bad Key': 'innocent' },
+      });
+      check(r.valid === false, 'space in header key should reject');
+    });
+
+    test('non-string tls rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, tls: 'evil directive' });
+      check(r.valid === false, 'whitespace+word tls should reject');
+    });
+
+    test('empty authService when auth=true rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, auth: true });
+      check(r.valid === false, 'auth=true requires authService');
+    });
+
+    test('upstreamProtocol other than http/https rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, upstreamProtocol: 'javascript' });
+      check(r.valid === false, 'non-http protocol should reject');
+    });
+
+    test('stripPrefix without leading slash rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, stripPrefix: 'app/v1' });
+      check(r.valid === false, 'stripPrefix without leading slash should reject');
+    });
+
+    test('stripPrefix with brace rejected', () => {
+      const r = validateGenerationConfig({ ...BASE_OK, stripPrefix: '/api/{evil}' });
+      check(r.valid === false, 'stripPrefix with brace should reject');
+    });
+
+    test('multiple errors returned together (enumerable)', () => {
+      const r = validateGenerationConfig({
+        domain: 'evil }',
+        upstream: 'localhost:8080 } malicious {',
+        tls: 'bad tls',
+        auth: true,
+        headers: { 'X B': 'oops' },
+      });
+      check(r.valid === false, 'should reject');
+      check(r.errors.length >= 4, `expected multiple errors, got ${r.errors.length}: ${JSON.stringify(r.errors)}`);
+    });
+  });
+
+  describe('escapeCaddyQuotedString', () => {
+    test('escapes backslash and quote', () => {
+      check(escapeCaddyQuotedString('a"b\\c') === 'a\\"b\\\\c', 'should escape both');
+    });
+
+    test('safe string passes through verbatim', () => {
+      check(escapeCaddyQuotedString('hello') === 'hello', 'safe string unchanged');
+    });
+
+    test('empty string survives', () => {
+      check(escapeCaddyQuotedString('') === '', 'empty string survives');
+    });
+  });
+
+  describe('generateSiteBlock — quote-breakout defence-in-depth', () => {
+    test('post-validation, header value with " is properly escaped', () => {
+      // The validator REJECTS this upstream (CRLF + quote) but the
+      // generator must also escape `"` even if a future code path bypasses
+      // validation. This test pins the dual-defence.
+      const cfg = {
+        domain: 'app.example.com',
+        upstream: 'localhost:8080',
+        headers: { 'X-Custom': 'a"b' },
+      };
+      // The validator rejects CRLF + chars outside the charset, but a bare
+      // `"` is technically allowed by /[\r\n]/ (only CR/LF). However the
+      // GENERATOR must still escape it. Verify by calling generateSiteBlock
+      // directly with a manually-validated config.
+      const out = generateSiteBlock(cfg);
+      // The header line should appear as:   X-Custom "a\"b"
+      // i.e. the raw `"` in the value MUST be escaped, otherwise the Caddyfile
+      // line breaks out of the quoted context.
+      check(out.includes('X-Custom "a\\"b"'), `expected escaped quote, got: ${out}`);
+    });
+  });
+
+  describe('route integration — /caddycode/generate wires validation', () => {
+    const express = require('express');
+    const request = require('supertest');
+    const routes = require('../../routes/caddycode');
+
+    function buildApp() {
+      const app = express();
+      app.use(express.json());
+      const wrap = (fn) => (req, res, next) => Promise.resolve(fn(req, res, next)).catch(next);
+      return { app, wrap };
+    }
+
+    test('valid config → 200 + caddyfile', async () => {
+      const { app, wrap } = buildApp();
+      app.use('/api/v1', routes({ asyncHandler: wrap }));
+      const res = await request(app)
+        .post('/api/v1/caddycode/generate')
+        .send({ domain: 'app.example.com', upstream: 'localhost:8080' });
+      check(res.status === 200, `expected 200, got ${res.status}`);
+      check(typeof res.body.caddyfile === 'string', 'expected caddyfile string');
+      check(res.body.caddyfile.includes('app.example.com'), 'caddyfile should include domain');
+    });
+
+    test('CRLF in domain → 400 + enumerable errors', async () => {
+      const { app, wrap } = buildApp();
+      app.use('/api/v1', routes({ asyncHandler: wrap }));
+      const res = await request(app)
+        .post('/api/v1/caddycode/generate')
+        .send({ domain: 'evil.com\nnew block', upstream: 'localhost:8080' });
+      check(res.status === 400, `expected 400, got ${res.status}: ${JSON.stringify(res.body)}`);
+      check(res.body.success === false, 'success should be false');
+      check(Array.isArray(res.body.errors), `expected enumerable errors array, got body=${JSON.stringify(res.body)}`);
+      check(res.body.errors.length >= 1, 'at least one error');
+    });
+
+    test('"://" in upstream → 400', async () => {
+      const { app, wrap } = buildApp();
+      app.use('/api/v1', routes({ asyncHandler: wrap }));
+      const res = await request(app)
+        .post('/api/v1/caddycode/generate')
+        .send({ domain: 'app.example.com', upstream: 'http://evil.tld/x' });
+      check(res.status === 400, `expected 400, got ${res.status}`);
+    });
+
+    test('header with CRLF → 400 + specific error', async () => {
+      const { app, wrap } = buildApp();
+      app.use('/api/v1', routes({ asyncHandler: wrap }));
+      const res = await request(app)
+        .post('/api/v1/caddycode/generate')
+        .send({
+          domain: 'app.example.com',
+          upstream: 'localhost:8080',
+          headers: { 'X-Bad': 'oops\r\nHost: evil.tld' },
+        });
+      check(res.status === 400, `expected 400, got ${res.status}`);
+      check(res.body.errors.some((e) => /CR or LF/i.test(e)), `expected CR/LF mention: ${JSON.stringify(res.body.errors)}`);
+    });
+
+    test('end-to-end: header value with quote + backslash round-trips through generator', async () => {
+      // DC-070 round-2 polish (per GLM-5.3 review): the unit tests pin the
+      // escape helper and the route reject path independently, but nothing
+      // asserts the GENERATED Caddyfile is well-formed when a header value
+      // contains BOTH " and \. Verify the generator escapes both so the
+      // resulting line parses as a Caddyfile quoted string.
+      const { app, wrap } = buildApp();
+      app.use('/api/v1', routes({ asyncHandler: wrap }));
+      const res = await request(app)
+        .post('/api/v1/caddycode/generate')
+        .send({
+          domain: 'app.example.com',
+          upstream: 'localhost:8080',
+          headers: { 'X-Custom': 'a"b\\c' },
+        });
+      check(res.status === 200, `expected 200, got ${res.status}: ${JSON.stringify(res.body)}`);
+      const out = res.body.caddyfile;
+      check(typeof out === 'string', 'expected caddyfile string');
+      // The header line should be EXACTLY:  X-Custom "a\"b\\c"
+      // i.e. the raw `"` and `\` in the value MUST be escaped.
+      check(
+        /X-Custom "a\\"b\\\\c"/.test(out),
+        `expected escaped quote+backslash in generated Caddyfile, got: ${out}`
+      );
+    });
+  });
+});

dashcaddy-api/routes/caddycode.js

@@ -11,10 +11,138 @@
  */
 const express = require('express');
 const { ok, errorResponse } = require('../src/utils/responses');
+const { REGEX } = require('../src/utilities/constants');
+
+/**
+ * DC-070: Validate the structural config that flows into generateSiteBlock.
+ *
+ * Threat model: `generateSiteBlock` interpolates user-controlled fields
+ * (domain, tls, authService, headers.*, stripPrefix, upstream) DIRECTLY into
+ * a Caddyfile text block that is later fed to `caddy.modify()` and the
+ * Caddy admin /load endpoint. The /caddycode/generate endpoint is
+ * authenticated (forward_auth gated), but the bug class is "compromised
+ * middleware / pivot" — a JSON-only payload can be smuggled past any
+ * UI-side input checks.
+ *
+ * Pre-fix, every field was trusted: `lines.push(`${domain} {`)` accepted any
+ * string (including newlines that close the block and inject a new site),
+ * `headers[key] = "${value}"` accepted arbitrary quotes (which would break
+ * the surrounding `"..."` Caddy quoted-string context and inject directives),
+ * and `tls`, `authService`, `stripPrefix`, `upstream` had no charset
+ * restrictions at all (spaces, braces, semicolons would land verbatim).
+ *
+ * Post-fix: every field is constrained to a known-safe character class
+ * BEFORE interpolation, and CRLF is rejected outright. Quoted-string
+ * injection in header values is closed by escaping `\` and `"` per the
+ * Caddy quoted-string spec (backslash escapes the next character).
+ */
+function validateGenerationConfig(config) {
+  const errors = [];
+  const {
+    domain,
+    upstream,
+    upstreamProtocol = 'http',
+    tls = 'auto',
+    auth = false,
+    authService = null,
+    headers = {},
+    stripPrefix = null,
+  } = config;
+
+  // 1. domain — RFC 1123 hostname. Reject anything with whitespace, brace,
+  //    semicolon, newline, or non-printable. REGEX.DOMAIN is
+  //    /^[a-z0-9]([a-z0-9.-]{0,251}[a-z0-9])?$/i in constants.js.
+  if (typeof domain !== 'string' || !REGEX.DOMAIN.test(domain)) {
+    errors.push('domain must be a valid hostname (letters, digits, dots, hyphens)');
+  }
+
+  // 2. upstream — `host:port` form (the only shape Caddy's reverse_proxy
+  //    directive takes for non-URL upstreams). Reject `://`, whitespace,
+  //    braces. Allow optional IPv6 bracket form `[::1]:5000`. Must
+  //    include an explicit :port segment — a bare `localhost` would
+  //    produce a Caddyfile that fails to reload (port required for
+  //    reverse_proxy upstreams). Two regex branches: (a) bare host with
+  //    required :port, (b) bracketed IPv6 literal with required :port.
+  if (typeof upstream !== 'string'
+      || !/^[a-z0-9.\-]+:\d{1,5}$/i.test(upstream)
+      && !/^\[[a-z0-9.\-:.]+\]:\d{1,5}$/i.test(upstream)
+  ) {
+    errors.push('upstream must be host:port (host letters/digits/dots/hyphens, port 1-65535, optional IPv6 brackets)');
+  }
+
+  // 3. tls — either the literal strings 'auto' / 'internal' (handled
+  //    specially below) OR a CA name like 'letsencrypt' / 'internal' that
+  //    must match /^[a-z0-9._-]+$/i. Reject whitespace + braces + quotes.
+  if (typeof tls !== 'string' || !/^[a-z0-9._-]+$/i.test(tls)) {
+    errors.push('tls must be one of: auto, internal, or a CA name (letters, digits, dots, underscores, hyphens)');
+  }
+
+  // 4. authService — only meaningful when auth=true; otherwise ignore. Must
+  //    match the existing SSO service-id charset (REGEX.SUBDOMAIN).
+  if (auth) {
+    if (typeof authService !== 'string' || !REGEX.SUBDOMAIN.test(authService)) {
+      errors.push('authService must be a valid subdomain (lowercase, alphanumeric, hyphens)');
+    }
+  }
+
+  // 5. upstreamProtocol — only 'http' or 'https'. Anything else gets coerced
+  //    to 'http' but only after we explicitly accept it; reject obvious
+  //    injection vectors here.
+  if (upstreamProtocol !== 'http' && upstreamProtocol !== 'https') {
+    errors.push('upstreamProtocol must be "http" or "https"');
+  }
+
+  // 6. headers — each key must be a valid HTTP header name ([A-Za-z0-9-]+),
+  //    each value must be a string with no CR/LF and no unescaped quotes.
+  if (headers && typeof headers === 'object') {
+    for (const [key, value] of Object.entries(headers)) {
+      if (typeof key !== 'string' || !/^[A-Za-z0-9-]+$/.test(key)) {
+        errors.push(`header key "${String(key)}" must be HTTP-token chars only ([A-Za-z0-9-])`);
+      }
+      if (typeof value !== 'string') {
+        errors.push(`header "${key}" value must be a string`);
+        continue;
+      }
+      if (/[\r\n]/.test(value)) {
+        errors.push(`header "${key}" value must not contain CR or LF`);
+      }
+    }
+  }
+
+  // 7. stripPrefix — must be a leading-slash path with safe chars. Reject
+  //    braces, quotes, whitespace, and { } which would let the attacker
+  //    open a new Caddyfile block.
+  if (stripPrefix != null) {
+    if (typeof stripPrefix !== 'string' || !/^\/[A-Za-z0-9._\-/]*$/.test(stripPrefix)) {
+      errors.push('stripPrefix must be an absolute path (letters, digits, dots, hyphens, slashes)');
+    }
+  }
+
+  return { valid: errors.length === 0, errors };
+}
+
+/**
+ * Escape a string for safe interpolation inside a Caddyfile quoted-string
+ * context. Caddy uses the same backslash-escape semantics as JSON-ish
+ * contexts — `\` and `"` MUST be escaped, otherwise the attacker breaks out
+ * of the quoted string and injects arbitrary directives.
+ *
+ * @param {string} s raw header value
+ * @returns {string} escaped value (no embedded newlines; CR/LF were already
+ *   rejected by the validator)
+ */
+function escapeCaddyQuotedString(s) {
+  return String(s).replace(/\\/g, '\\\\').replace(/"/g, '\\"');
+}
 
 /**
  * Generate a Caddyfile site block from a structured config.
- * @param {Object} config - Site configuration
+ *
+ * Every interpolated field is now validated by `validateGenerationConfig`
+ * first (see DC-070). Quoted-string values are escaped via
+ * `escapeCaddyQuotedString` so a `"` in a header value cannot break out.
+ *
+ * @param {Object} config - Site configuration (already validated)
  * @returns {string} Caddyfile snippet
  */
 function generateSiteBlock(config) {
@@ -38,12 +166,15 @@ function generateSiteBlock(config) {
   const lines = [];
   lines.push(`${domain} {`);
 
-  // TLS
+  // TLS — only emit a tls directive when explicitly 'internal' or a CA
+  // name; 'auto' means Caddy's default behaviour (no directive needed).
   if (tls === 'internal') {
     lines.push(`  tls internal`);
   } else if (tls === 'auto') {
     // Default — Caddy auto-provisions Let's Encrypt
-  } else if (typeof tls === 'string') {
+  } else {
+    // CA name validated by validateGenerationConfig against
+    // /^[a-z0-9._-]+$/i — safe to interpolate verbatim.
     lines.push(`  tls ${tls}`);
   }
 
@@ -52,7 +183,8 @@ function generateSiteBlock(config) {
     lines.push(`  # Redirect HTTP to HTTPS is automatic in Caddy 2`);
   }
 
-  // Auth gate (DashCaddy forward_auth)
+  // Auth gate (DashCaddy forward_auth) — authService validated by
+  // validateGenerationConfig against REGEX.SUBDOMAIN — safe to interpolate.
   if (auth && authService) {
     lines.push(`  import dashcaddy_auth ${authService}`);
   }
@@ -66,16 +198,17 @@ function generateSiteBlock(config) {
     lines.push(`  }`);
   }
 
-  // Custom headers
+  // Custom headers — keys validated against /^[A-Za-z0-9-]+$/, values
-  if (Object.keys(headers).length > 0) {
+  // escaped via escapeCaddyQuotedString before being placed inside "..."
+  if (headers && typeof headers === 'object' && Object.keys(headers).length > 0) {
     lines.push(`  header {`);
     for (const [key, value] of Object.entries(headers)) {
-      lines.push(`    ${key} "${value}"`);
+      lines.push(`    ${key} "${escapeCaddyQuotedString(value)}"`);
     }
     lines.push(`  }`);
   }
 
-  // Strip prefix
+  // Strip prefix — validated to /^\/[A-Za-z0-9._\-/]*$/ — safe.
   if (stripPrefix) {
     lines.push(`  uri strip_prefix ${stripPrefix}`);
   }
@@ -118,6 +251,19 @@ module.exports = function({ asyncHandler }) {
       return errorResponse(res, 400, 'upstream is required (e.g. localhost:8080)');
     }
 
+    // DC-070: structural validation BEFORE interpolation. Every field that
+    // flows into the Caddyfile text must satisfy a known-safe charset rule,
+    // and CRLF is rejected outright. Run this BEFORE generateSiteBlock so
+    // the bad input is rejected with a clean 400 + enumerable error list,
+    // not a generated-Caddyfile + 500.
+    const validation = validateGenerationConfig(config);
+    if (!validation.valid) {
+      return errorResponse(res, 400, 'Invalid configuration', {
+        code: 'DC-CCD-700',
+        errors: validation.errors,
+      });
+    }
+
     try {
       const caddyfile = generateSiteBlock(config);
       ok(res, { caddyfile, config });
@@ -225,3 +371,11 @@ module.exports = function({ asyncHandler }) {
 
   return router;
 };
+
+// DC-070: export helpers for unit-testing the sanitization surface
+// independently of the route handler.
+module.exports.__test = {
+  validateGenerationConfig,
+  escapeCaddyQuotedString,
+  generateSiteBlock,
+};