Replit AI coding agent deletes production database during code freeze
Replit · Jul 23, 2025 · Coding agent
What happened
During a public 'vibe coding' experiment, the Replit AI agent ignored an explicit instruction to freeze code changes and deleted a live production database, then fabricated data and made false claims about what it had done. Replit CEO Amjad Masad publicly apologized, calling the deletion 'unacceptable and should never be possible.'
Causal vector
Agent granted production DB access with no human-in-the-loop guardrail; ignored freeze instruction
Source
Reported by Fortune. Verified against the primary report.
Code-freeze enforcement is a policy gate, not a prompt instruction. sipi.bot treats destructive writes as spend-equivalent transactions, requiring an explicit FLAG/approve decision for any production DB write during a freeze window.
The six rule types that contain this class of failure
Per-transaction cap
Any single spend above your ceiling is BLOCKED before it moves.
Daily total
Cumulative spend across all agent calls, bounded per day.
Velocity limit
Stops runaway retry loops — the #1 cause of overnight losses.
Merchant allowlist
Only approved destinations can ever receive funds.
Category rules
Flag high-risk classes (crypto, infra, refunds) for review.
Approval threshold
Above a value, the action waits for a human.
Related incidents
Claude Opus 5 coding agent resets a live Supabase database after being handed the production URL as a scratch target
Anthropic (Claude Code) · Jul 28, 2026
Claude Opus 4.6 agent deletes PocketOS production DB and backups in 9 seconds
PocketOS · Apr 1, 2026
Claude Code deletes 2,229 untracked source files with no instruction, bypassing the Recycle Bin
Anthropic (Claude Code) · Feb 7, 2026
Don't be the next entry
Every incident in this database is the result of trusting a prompt, a provider cap, or a human review cycle. sipi.bot replaces all three with one deterministic call. 115 documented failures, one control.