Reverse engineering a $1B Legal AI tool exposed 100k+ confidential files
TL;DR Highlight
Filevine's legal AI SaaS had a public API endpoint returning Box admin tokens without auth, exposing 100K+ confidential files from law firms.
Who Should Read
Security engineers and backend devs building SaaS products with third-party OAuth integrations, and CTOs evaluating legal AI vendors.
Core Mechanics
- Filevine had a publicly accessible API endpoint that returned Box admin tokens without any authentication — a classic insecure direct object reference issue on a privileged token endpoint.
- The exposed tokens gave access to Box admin accounts belonging to law firm customers, meaning confidential legal documents (over 100K files) were readable by anyone who hit the endpoint.
- The researcher reported the vulnerability responsibly, but initial response from Filevine was slow. The issue was eventually patched.
- This is a textbook OAuth token storage failure: the server-side tokens were returned client-side with no authorization check on the caller.
- The attack surface is especially sensitive here — legal SaaS products hold privileged client communications, case files, and court documents that carry attorney-client privilege.
Evidence
- The researcher documented the endpoint, sample request, and sanitized token response, confirming the unauthenticated access was trivially reproducible.
- Community reaction was strong: several commenters noted this is a systemic problem with 'move fast' SaaS culture when applied to high-sensitivity legal data.
- Others pointed out that law firms face ABA ethics rules around client data confidentiality — a breach like this could expose firms to bar complaints in addition to legal liability.
- There was debate about whether Filevine's response timeline was acceptable for a security incident of this severity.
How to Apply
- Audit all endpoints that return OAuth tokens or third-party API credentials — verify that caller authorization is checked, not just authentication.
- Never store third-party admin tokens in a way that's retrievable via a user-facing API without checking the requester's permission scope.
- For legal/medical/financial SaaS: treat third-party integration tokens as secrets with the same access controls you'd apply to raw credentials.
- Add automated tests for your most sensitive API endpoints that explicitly verify unauthenticated requests are rejected with 401/403.
Code Example
// Vulnerable pattern: frontend directly receives a high-privilege token and calls external API
const res = await fetch(`${BOX_SERVICE}/recommend`, {
method: 'POST',
body: JSON.stringify({ projectName: 'Very sensitive Project' })
// No Authorization header!
});
const { boxToken } = await res.json(); // admin token is returned as-is
// Safe pattern: backend acts as proxy or issues short-lived presigned URLs
// Backend (Node.js example)
app.get('/api/file/:fileId', authenticate, async (req, res) => {
// 1. Verify user permissions
const hasAccess = await checkPermission(req.user, req.params.fileId);
if (!hasAccess) return res.status(403).json({ error: 'Forbidden' });
// 2. Call Box API using a token stored only on the backend
const boxClient = new BoxClient({ accessToken: process.env.BOX_ADMIN_TOKEN });
const downloadUrl = await boxClient.files.getDownloadURL(req.params.fileId);
// 3. Return only a short-lived URL (no direct token exposure)
res.json({ url: downloadUrl, expiresIn: 60 });
});Terminology
Related Papers
Show HN: Mindwalk – Replay coding-agent sessions on a 3D map of your codebase
Claude Code나 Codex 같은 AI 코딩 에이전트가 세션 중 코드베이스의 어떤 파일을 탐색하고 수정했는지를 3D 지도 형태로 시각화해서 재생해주는 로컬 도구다. 에이전트가 작업을 어떻게 이해했는지 한눈에 파악할 수 있다.
Ghost Font: A font that humans can read but AI cannot
움직임(모션)을 이용해 글자를 표현해서 AI 모델이 정적 이미지 분석으로는 메시지를 해독하지 못하게 막는 실험적 프로젝트인데, 커뮤니티에서는 이미 GPT-5.6, Claude Opus 등으로 해독에 성공한 사례가 속출해 실효성 논쟁이 뜨겁다.
GPT-5.6, Grok 4.5, Claude, and Muse Spark build the same 4 apps
12개 LLM 모델에게 레이캐스터 미로, 루빅스 큐브, 계산기, Game of Life 앱을 각각 5번씩 만들게 해서 성공률·비용·속도를 비교한 실전 벤치마크다. GPT-5.6 Sol이 전반적으로 가장 일관된 결과를 냈고, Grok 4.5는 가성비 면에서 눈에 띄었다.
Benchmarking coding agents on Databricks' multi-million line codebase
Databricks가 자사 실제 코드베이스를 기반으로 여러 AI 코딩 에이전트의 성능과 비용을 직접 측정했고, 모델 토큰 가격과 실제 태스크 비용이 전혀 다르다는 점, 그리고 오픈소스 모델이 이제 최상위 수준에 도달했다는 점을 확인했다.
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
LLM이 저자원 언어 질문을 받을 때 영어로 추론하게 하면 불확실성 추정 성능이 고자원 언어 수준으로 올라온다.
LLM-as-a-Verifier: A General-Purpose Verification Framework
LLM의 토큰 확률 분포를 활용해 discrete 점수 대신 continuous 점수를 뽑아내면, 추가 학습 없이 코딩·로봇·의료 에이전트 평가 정확도를 SOTA로 끌어올릴 수 있다.