LLM-integrated code assistants
Incidents implicated systems
Incidente 11525 Reportes
LLM-Driven Replit Agent Reportedly Executed Unauthorized Destructive Commands During Code Freeze, Leading to Loss of Production Data
2025-07-18
An AI-powered development assistant on Replit's platform reportedly deleted a live production database during an active code freeze, despite receiving repeated instructions not to make changes. The system also reportedly produced fabricated test results and fake data, and incorrectly claimed rollback was impossible, delaying recovery. The incident reportedly resulted in significant data loss and user distrust regarding its safety and reliability.
MásIncidente 16714 Reportes
OpenAI GPT-5.6 Sol Agent Reportedly Deleted Most Files in AI Startup Founder's Mac Home Directory
2026-07-10
AI investor Matt Shumer reported that a GPT-5.6 Sol agent in OpenAI Codex's high-autonomy Ultra mode accidentally deleted most files in his Mac home directory during a cleanup task. A review sub-agent reportedly misexpanded $HOME and ran `rm -rf /Users/mattsdevbox`; Shumer stopped the process after material deletion. OpenAI later confirmed unauthorized file-deletion reports and said it was adding safeguards.
MásIncidente 16724 Reportes
OpenAI GPT-5.6 Sol Reportedly Deleted Software Engineer's Production Database During Local Testing
2026-07-13
Software engineer Bruno Lemos reported that GPT-5.6 Sol deleted his production database after he asked it to generate seed data for local testing. The agent reportedly ran the test suite, then initiated cleanup that executed TRUNCATE TABLE users CASCADE against production because the repo's test database URL pointed to the live Neon database. OpenAI later acknowledged unauthorized deletion reports and said it was adding safeguards.
MásIncidente 17234 Reportes
Anthropic's Claude Code AI Coding Tool Reportedly Used Hidden Unicode Markers to Classify Custom API Routing
2026-04-02
Researchers found that Anthropic's Claude Code AI coding tool classified custom API endpoint hostnames and two system timezones, encoding the results in system prompts with visually similar Unicode apostrophes and altered date separators. Anthropic said the mechanism was an anti-reseller and anti-distillation experiment launched in March and removed it after disclosure.
MásEntidades relacionadas
Otras entidades que están relacionadas con el mismo incidente. Por ejemplo, si el desarrollador de un incidente es esta entidad pero el implementador es otra entidad, se marcan como entidades relacionadas.
Entidades relacionadas
Anthropic
Incidentes involucrados como desarrollador e implementador
Incidents involved as Developer
AI agent system users
Afectado por Incidentes
- Incidente 16714 Report
OpenAI GPT-5.6 Sol Agent Reportedly Deleted Most Files in AI Startup Founder's Mac Home Directory
- Incidente 16724 Report
OpenAI GPT-5.6 Sol Reportedly Deleted Software Engineer's Production Database During Local Testing
Incidents involved as Deployer
Software developers
Afectado por Incidentes
- Incidente 16724 Report
OpenAI GPT-5.6 Sol Reportedly Deleted Software Engineer's Production Database During Local Testing
- Incidente 16763 Report
Anthropic Claude Opus 5 Coding Agent Reportedly Reset a Live Supabase Production Database During Prisma Migration Work
Incidents involved as Deployer
Users of production portal disrupted during Gemini 3.5 coding-agent incident
Afectado por Incidentes
AI coding assistant users
Afectado por Incidentes
- Incidente 17234 Report
Anthropic's Claude Code AI Coding Tool Reportedly Used Hidden Unicode Markers to Classify Custom API Routing
- Incidente 17191 Report
Anthropic's Claude Code AI Agent Reportedly Deleted About 48,000 Live Project Files and Version-Control History During Software Repair