This database can't measure reliability: it collects reported failures, with no count of how often Lovable is used. Among its 3 documented incidents, the average severity is 8.7/10; 2 were rated critical and 1 high.

What are the most common Lovable failures?

The most common failure mode is security vulnerability. Lovable has 2 critical incidents.

How many Lovable AI failures have been documented?

StupidLLM has documented 3 Lovable AI agent failures. Each incident is severity-scored on a published 0-10 rubric and linked to its source.

Agent report

Lovable failures

3 documented incidents, average severity 8.7/10. Most common failure mode: security vulnerability.

n = 3

Incidents

8.7

Avg severity

Critical

Source checked

Severity breakdown

Stacked severity breakdown per agent. Longer bar = more incidents.

Failure modes

Distribution of failure modes across all documented incidents.

Worst documented incident

9.0

critical

A broken object-level authorization bug let any free Lovable account pull other users' source code, Supabase credentials and AI chat histories for 48 days before Lovable fixed it

All 3 incidents

STUPID-2026-0149

9.0

A broken object-level authorization bug let any free Lovable account pull other users' source code, Supabase credentials and AI chat histories for 48 days before Lovable fixed it STUPID-2026-0031

9.0

Lovable-generated apps shipped without adequate Supabase row-level security, leaving databases readable and writable by anyone (CVE-2025-48757)STUPID-2026-0151

8.0

A security researcher found 16 vulnerabilities — including inverted access-control logic — in a Lovable-generated EdTech app, exposing 18,697 users' records and letting anyone delete accounts or grade exams