Validate first-party parser boundaries

scraper/plugins/client.js

@@ -1,20 +1,35 @@
 'use strict';
 
 const { parse } = require('./registry');
+const { validate } = require('./validation');
+const MAX_MESSAGE_BYTES = 2 * 1024 * 1024;
+
+async function boundedJson(response) {
+  const chunks = [];
+  let bytes = 0;
+  for await (const chunk of response.body) {
+    bytes += chunk.length;
+    if (bytes > MAX_MESSAGE_BYTES) throw new Error('Source plugin response exceeds limit');
+    chunks.push(chunk);
+  }
+  return JSON.parse(Buffer.concat(chunks).toString('utf8'));
+}
 
 async function parseSource(plugin, operation, input) {
   const endpoint = process.env.SOURCE_PLUGIN_URL;
-  if (!endpoint) return parse(plugin, operation, input);
+  if (!endpoint) return validate(plugin, operation, parse(plugin, operation, input));
   const url = new URL('/v1/parse', endpoint);
   if (!['http:', 'https:'].includes(url.protocol)) throw new Error('Invalid source plugin endpoint');
+  const body = JSON.stringify({ plugin, operation, input });
+  if (Buffer.byteLength(body) > MAX_MESSAGE_BYTES) throw new Error('Source plugin request exceeds limit');
   const response = await fetch(url, {
     method: 'POST',
     headers: { 'content-type': 'application/json' },
-    body: JSON.stringify({ plugin, operation, input }),
+    body,
     signal: AbortSignal.timeout(10000),
   });
   if (!response.ok) throw new Error(`Source parser unavailable (${response.status}); checkpoint preserved`);
-  return response.json();
+  return validate(plugin, operation, await boundedJson(response));
 }
 
 module.exports = { parseSource };

scraper/plugins/validation.js

@@ -0,0 +1,47 @@
+'use strict';
+
+const net = require('node:net');
+
+function sourceUrl(value, prefix) {
+  const url = new URL(value);
+  if (url.protocol !== 'https:' || url.hostname !== 'weebcentral.com' || url.username || url.password || !url.pathname.startsWith(prefix)) {
+    throw new Error('Source plugin returned an unexpected WeebCentral URL');
+  }
+  return url.href;
+}
+
+function imageUrl(value) {
+  const url = new URL(value);
+  const hostname = url.hostname.toLowerCase();
+  if (url.protocol !== 'https:' || url.username || url.password || net.isIP(hostname)
+    || hostname === 'localhost' || hostname.endsWith('.localhost') || hostname.endsWith('.local')
+    || !hostname.includes('.')) {
+    throw new Error('Source plugin returned an unsafe image URL');
+  }
+  return url.href;
+}
+
+function validate(plugin, operation, output) {
+  if (plugin !== 'weebcentral' || !output || typeof output !== 'object' || Array.isArray(output)) {
+    throw new Error('Invalid source plugin output');
+  }
+  if (operation === 'series') {
+    if (typeof output.title !== 'string' || typeof output.listUrl !== 'string' && output.listUrl !== null) throw new Error('Invalid series parse');
+    if (output.listUrl !== null) sourceUrl(output.listUrl, '/series/');
+  } else if (operation === 'catalog') {
+    if (!Array.isArray(output.chapters) || !Number.isInteger(output.chapterLinks) || output.chapterLinks < 0) throw new Error('Invalid catalog parse');
+    for (const chapter of output.chapters) {
+      if (!chapter || typeof chapter.id !== 'string' || typeof chapter.number !== 'string') throw new Error('Invalid chapter reference');
+      sourceUrl(chapter.url, '/chapters/');
+    }
+  } else if (operation === 'chapter') {
+    sourceUrl(output.manifestUrl, '/chapters/');
+    if (!new URL(output.manifestUrl).pathname.endsWith('/images')) throw new Error('Invalid chapter image manifest');
+  } else if (operation === 'pages') {
+    if (!Array.isArray(output.pages)) throw new Error('Invalid page parse');
+    for (const page of output.pages) imageUrl(page);
+  } else throw new Error('Unknown source plugin operation');
+  return output;
+}
+
+module.exports = { validate };

scraper/test/source-plugin.test.js

@@ -2,9 +2,11 @@
 
 const test = require('node:test');
 const assert = require('node:assert/strict');
+const httpModule = require('node:http');
 const { createServer } = require('../plugins/worker');
 const { parse } = require('../plugins/registry');
 const { parseSource } = require('../plugins/client');
+const { validate } = require('../plugins/validation');
 const { discoverWeebCatalog, discoverWeebChapter } = require('../adapters/weebcentral');
 
 const seriesUrl = 'https://weebcentral.com/series/ABC/title';
@@ -21,6 +23,15 @@ test('first-party registry rejects unknown plugins and malformed input', () => {
   assert.equal(parse('weebcentral', 'catalog', { html: listHtml, url: seriesUrl }).chapters.length, 2);
 });
 
+test('parser output cannot turn catalog and image links into local or unrelated requests', () => {
+  assert.throws(() => validate('weebcentral', 'series', { title: 'X', listUrl: 'http://127.0.0.1:8091/api/state' }), /unexpected/);
+  assert.throws(() => validate('weebcentral', 'catalog', { chapterLinks: 1, chapters: [{ id: 'X', number: '1', url: 'https://other.example/chapters/X' }] }), /unexpected/);
+  assert.throws(() => validate('weebcentral', 'chapter', { manifestUrl: 'https://weebcentral.com/chapters/X/not-images' }), /manifest/);
+  assert.throws(() => validate('weebcentral', 'pages', { pages: ['http://127.0.0.1:8080/private'] }), /unsafe/);
+  assert.throws(() => validate('weebcentral', 'pages', { pages: ['https://localhost/private'] }), /unsafe/);
+  assert.doesNotThrow(() => validate('weebcentral', 'pages', { pages: ['https://img.example/1.jpg'] }));
+});
+
 test('isolated parser preserves WeebCentral catalog and page discovery', async () => {
   const server = createServer();
   await new Promise(resolve => server.listen(0, '127.0.0.1', resolve));
@@ -65,3 +76,20 @@ test('configured worker failure does not fall back to local parsing', async () =
     else process.env.SOURCE_PLUGIN_URL = previous;
   }
 });
+
+test('scraper rejects unsafe responses from a configured worker', async () => {
+  const server = httpModule.createServer((_request, response) => {
+    response.writeHead(200, { 'content-type': 'application/json' });
+    response.end(JSON.stringify({ title: 'X', listUrl: 'http://127.0.0.1:8091/api/state' }));
+  });
+  await new Promise(resolve => server.listen(0, '127.0.0.1', resolve));
+  const previous = process.env.SOURCE_PLUGIN_URL;
+  process.env.SOURCE_PLUGIN_URL = `http://127.0.0.1:${server.address().port}`;
+  try {
+    await assert.rejects(parseSource('weebcentral', 'series', { html: seriesHtml, url: seriesUrl }), /unexpected/);
+  } finally {
+    if (previous === undefined) delete process.env.SOURCE_PLUGIN_URL;
+    else process.env.SOURCE_PLUGIN_URL = previous;
+    await new Promise(resolve => server.close(resolve));
+  }
+});