Production rescue
AI App Security Audit
Short answer
AI-built apps fail security in predictable ways: keys in the browser, missing row-level security, IDOR on APIs, and LLM endpoints that will happily read another tenant’s documents.
What is an AI app security audit?
A review focused on the failure modes of generated apps and LLM features — not a generic ISO checklist. Priority: data isolation and secret handling.
Common AI-app failures
| Bug | Why generators create it | Fix |
|---|---|---|
| Client-side API key | Demo code copies the quickstart | Server route + usage caps |
| No RLS | Tables “just work” | Policies per tenant |
| IDOR | Routes use IDs from the URL | Authz on every load |
| Prompt injection | User text concatenated into system prompt | Isolation + allowlists |
Minimum bar before paying users
No secrets in the client bundle. Every read/write checks the current user (and org). File URLs expire. Stripe webhooks verify signatures. AI routes are rate-limited and logged.
LLM-specific
If users can upload docs, assume they will try to jailbreak retrieval. Do not put other tenants’ chunks in the same unconstrained context. Log token spend per user.
FAQ
Do I need a full pentest before launch?
Not for a 50-user MVP. You do need the items above. Pentest when you have a reason (enterprise buyer, compliance).
Related
Worried you shipped a key in the client?
That’s the #1 finding. We can hunt the rest — or you can start with the checklist on this page.