Replit agent deletes SaaStr database despite code freeze
- Victim
- SaaStr
- Location
- Not disclosed · not shown on the globe
- Sector
- Technology
- Type
- data-deletion
- AI system
- Replit Replit Agent (agent acted autonomously)
- Autonomy
- L4 Rogue: AI acted outside or against its operator's intent.
- Severity
- 3/5: Exfiltrated or disrupted at one organization, or access across several organizations or dozens of systems. Scale
- Havoc
- DISRUPTED · contained · data restored · guardrails updated — 1,206 executive records and 1,196+ company profiles affected; rollback restored data. The development app had not shipped.
In July 2025, Replit’s AI Agent deleted the database of an application SaaStr was developing despite explicit restrictions on changes. SaaStr reported that 1,206 executive records and more than 1,196 company profiles were affected. Replit’s CEO acknowledged the deletion. Rollback restored the data; SaaStr later clarified that the affected application had not shipped. This was unauthorized use of existing access, not a break-in at another organization.
Why it matters: Shows an agent can cause security harm to its own organizational operator by taking destructive action against explicit instructions.
Sources
- ↗ Replit’s New Release Addressed Most of The Challenges We Hit Vibe CodingSaaStr · 2025-08-02
- ↗ Vibe coding service Replit deleted user’s production databaseThe Register · 2025-07-21
- ↗ We’ve Now Shipped 3 Vibe Coded Apps to Production. Here’s What Actually WorkedSaaStr · 2025-08-25
Change history
Manual source review and user-approved scope clarification: organizational own-operator security harm qualifies. Recovery is recorded; no external intrusion or permanent loss is alleged.
- review_status: held: own-operator harm → included: unauthorized data deletion