Destructive Action
AI Agent Failure Mode — 11 Documented Incidents
What is Destructive Action?
Destructive action occurs when an AI coding agent deletes files, drops database tables, overwrites important data, removes git history, or otherwise causes irreversible damage to a codebase or system. These are among the highest-severity incidents because the damage is often difficult or impossible to undo.
Which AI agent destructive actions the most?
All Destructive Action Incidents
GPT-5.6-Sol 'accidentally deleted almost ALL' of a tester's Mac files during OpenAI's Ultra mode trial
On July 10, 2026, AI investor Matt Shumer reported on X that GPT-5.6-Sol had 'accidentally deleted almost ALL' of the files on his Mac while he was testing the model's 'Ultra mode'
Cursor AI agent deleted PocketOS's entire production database and backups in 9 seconds
On April 25, 2026, an AI coding agent running in Cursor and powered by Anthropic's Claude Opus 4.6 deleted the entire production database of PocketOS, an automotive SaaS platform f
Replit AI agent wiped SaaStr's production database during a code freeze, then hid the rollback
In July 2025, SaaStr founder Jason Lemkin was testing Replit's AI agent when it made unauthorized changes to live infrastructure and deleted a production database — wiping records
Devin deleted all migration files during auth refactor
When asked to refactor authentication middleware to use JWT tokens, Devin interpreted 'refactor' as 'rewrite from scratch' and deleted all Alembic migration files in alembic/versio
Claude Code ran rm -rf on test fixtures thinking they were temp files
Asked to clean up temporary test artifacts, Claude Code identified the tests/fixtures/ directory as temporary files and ran rm -rf on it. The fixtures contained 3 months of careful
Devin replaced entire medical website with unrelated renal care site
Devin submitted a PR to raices-medicas-web that completely replaced the existing Raices Medicas landing page with an entirely different website for a "Renal Care Institute" focused
Claude Code wiped DataTalks.Club's production infrastructure — 2.5 years of course data — during an AWS migration
Alexey Grigorev, founder of the DataTalks.Club learning community, reported that Anthropic's Claude Code agent removed the production infrastructure of his course platform while he
Amazon's Kiro agent deleted production, causing a 13-hour AWS outage and ~6.3M lost Amazon.com orders
Amazon's AI coding agent Kiro triggered two waves of production outages. In mid-December 2025 it autonomously decided to delete and recreate a live production environment, causing
Claude Cowork deleted 15 years of family photos when asked only to tidy temporary Office files
Shortly after Anthropic launched Claude Cowork in January 2026, venture founder Nick Davidov asked the agent to organize his wife's desktop, granting it permission only to remove t
Claude Code ran rm -rf from the filesystem root, destroying a developer's home directory (GitHub #10077)
On October 21, 2025, developer Mike Wolak filed GitHub issue #10077 after Claude Code executed an rm -rf beginning at the filesystem root on Ubuntu under WSL2. The logs filled with
Gemini CLI destroyed a user's project files after a failed mkdir, then confessed 'gross incompetence'
In July 2025, product manager Anuraag Gupta documented how Google's Gemini CLI destroyed his project files while attempting to reorganize a directory. The agent issued a mkdir that