mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-08-27 12:13:30 +00:00
96404bfc73
* fix: SSRF-guard speech (STT/TTS) and OCR outbound requests at connect time Speech (STT/TTS) and OCR issued outbound HTTP to operator-provided target URLs with only proxy config attached, so a target that resolves to a private, loopback, link-local, or cloud-metadata address was reachable by the server. This is the same class already guarded for the custom models fetch, Actions, avatar, MCP, and the OpenAI/Anthropic endpoint clients. Add one helper applySSRFSafeAgentIfDirect(config, url, allowedAddresses) that rejects non-http(s) or unparseable target URLs, sets maxRedirects to 0 so a redirect cannot bypass the connect-time check, and attaches createSSRFSafeAgents when no proxy or agent is already set (proxy precedence preserved). Wire it into the six speech/OCR call sites and thread each section's allowedAddresses exemption from pr-01. Scope is private/internal SSRF only. It does not restrict forwarding a credential to a public host, which is a separate egress-allowlist concern. Absent an allowedAddresses entry, private targets now fail closed, matching endpoints, actions, and MCP. Document the new fields in librechat.example.yaml with the operator warning that allowedAddresses hostnames are trusted before the private-IP check. * fix: block literal private-IP hosts and thread STT exemptions through generic uploads applySSRFSafeAgentIfDirect only attached the DNS-lookup agents, but Node skips the custom lookup for IP-literal hosts, so a literal private IP such as http://127.0.0.1 connected unchecked. Reject literal private IPs synchronously in the helper, reusing the same allowedAddresses exemption logic as the lookup path. The generic audio-upload path did not forward the section-level allowedAddresses to sttRequest, so a private STT endpoint permitted via speech.stt.allowedAddresses failed with ESSRF outside the speech route. Thread the exemption through files/audio.ts and widen the STTService type. * fix: derive effective SSRF port for literal IPs and validate OCR target before opening its stream The literal-IP precheck normalized an empty URL.port to '', so allowedAddresses exemptions on a default port (127.0.0.1:80, [::1]:443) never matched. Derive 80/443 from the scheme when the port is omitted. uploadDocumentToMistral opened the upload file stream before the SSRF check, so a blocked or malformed target threw with the descriptor still open. Run the proxy/SSRF setup before fs.createReadStream. Reword the librechat.example.yaml allowedAddresses guidance to prefer a private IP literal over a hostname, and reconcile the speech/OCR SSRF specs to assert the synchronous literal-IP block instead of driving the connect-time lookup that Node skips for IP literals. * fix: block literal private IPs before the proxy return, destroy OCR stream on failure, canonicalize IPv6 exemptions Move the literal-IP check above the proxy/agent early return so a literal private IP is rejected even when a proxy is configured; document that a forward proxy must be SSRF-enforcing. Wrap the Mistral upload post in try/finally and destroy the file stream, so an async connect-time block does not leak the descriptor. Canonicalize IP literals in normalizeAddressCandidate through the same URL serialization targets use, so IPv4-mapped and expanded IPv6 exemptions match.
91 lines
3 KiB
JavaScript
91 lines
3 KiB
JavaScript
jest.mock('axios');
|
|
jest.mock('@librechat/data-schemas', () => ({
|
|
logger: { warn: jest.fn(), error: jest.fn(), debug: jest.fn() },
|
|
}));
|
|
jest.mock('~/server/services/Config', () => ({ getAppConfig: jest.fn() }));
|
|
jest.mock('./streamAudio', () => ({
|
|
getRandomVoiceId: jest.fn(),
|
|
createChunkProcessor: jest.fn(),
|
|
splitTextIntoChunks: jest.fn(),
|
|
}));
|
|
|
|
const axios = require('axios');
|
|
const { STTService } = require('./STTService');
|
|
const { textToSpeech } = require('./TTSService');
|
|
|
|
afterEach(() => {
|
|
jest.restoreAllMocks();
|
|
axios.post.mockReset();
|
|
});
|
|
|
|
describe('STT sttRequest SSRF guard (real agent)', () => {
|
|
const audioFile = { originalname: 'a.wav', mimetype: 'audio/wav', size: 1 };
|
|
const audioBuffer = Buffer.from('audio');
|
|
const provider = { url: 'http://10.0.0.5:8080', apiKey: 'sk', model: 'whisper-1' };
|
|
|
|
it('blocks a private-IP provider url with ESSRF before any request goes out', async () => {
|
|
const service = new STTService();
|
|
await expect(
|
|
service.sttRequest('openai', provider, { audioBuffer, audioFile, language: '' }),
|
|
).rejects.toMatchObject({ code: 'ESSRF' });
|
|
expect(axios.post).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('exempts a host:port in the section allowedAddresses and sets maxRedirects 0 with agents', async () => {
|
|
axios.post.mockResolvedValue({ status: 200, data: { text: 'ok' } });
|
|
const service = new STTService();
|
|
|
|
await service.sttRequest('openai', provider, { audioBuffer, audioFile, language: '' }, [
|
|
'10.0.0.5:8080',
|
|
]);
|
|
|
|
const options = axios.post.mock.calls[0][2];
|
|
expect(options.maxRedirects).toBe(0);
|
|
expect(options.httpAgent).toBeDefined();
|
|
expect(options.httpsAgent).toBeDefined();
|
|
});
|
|
});
|
|
|
|
describe('TTS textToSpeech SSRF guard (real agent)', () => {
|
|
function buildReqRes(allowedAddresses) {
|
|
const req = {
|
|
body: { input: 'hi', voice: 'v1' },
|
|
user: { id: 'u1' },
|
|
config: {
|
|
speech: {
|
|
tts: {
|
|
...(allowedAddresses ? { allowedAddresses } : {}),
|
|
localai: { url: 'http://10.0.0.5:8080', apiKey: 'sk', voices: ['v1'] },
|
|
},
|
|
},
|
|
},
|
|
};
|
|
const res = {
|
|
setHeader: jest.fn(),
|
|
headersSent: false,
|
|
status: jest.fn(() => ({ end: jest.fn(), send: jest.fn() })),
|
|
end: jest.fn(),
|
|
};
|
|
return { req, res };
|
|
}
|
|
|
|
it('blocks a private-IP provider url and never issues the outbound request', async () => {
|
|
const { req, res } = buildReqRes();
|
|
|
|
await textToSpeech(req, res);
|
|
|
|
expect(axios.post).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('exempts a host:port in the section allowedAddresses and sets maxRedirects 0 with agents', async () => {
|
|
axios.post.mockResolvedValue({ status: 200, data: { pipe: jest.fn(), on: jest.fn() } });
|
|
const { req, res } = buildReqRes(['10.0.0.5:8080']);
|
|
|
|
await textToSpeech(req, res);
|
|
|
|
const options = axios.post.mock.calls[0][2];
|
|
expect(options.maxRedirects).toBe(0);
|
|
expect(options.httpAgent).toBeDefined();
|
|
expect(options.httpsAgent).toBeDefined();
|
|
});
|
|
});
|