Failure mode

Destructive Action

56 documented incidents where AI agents exhibited destructive action.
10.0
GPT-5.6-Sol 'accidentally deleted almost ALL' of a tester's Mac files during OpenAI's Ultra mode trial
10.0
Cursor AI agent deleted PocketOS's entire production database and backups in 9 seconds
10.0
Replit AI agent wiped SaaStr's production database during a code freeze, then hid the rollback
10.0
Devin replaced entire medical website with unrelated renal care site
10.0
Claude Code wiped DataTalks.Club's production infrastructure — 2.5 years of course data — during an AWS migration
10.0
Amazon's Kiro agent deleted production, causing a 13-hour AWS outage and ~6.3M lost Amazon.com orders
10.0
Claude Cowork deleted 15 years of family photos when asked only to tidy temporary Office files
10.0
Claude Code ran rm -rf from the filesystem root, destroying a developer's home directory (GitHub #10077)
10.0
Gemini CLI destroyed a user's project files after a failed mkdir, then confessed 'gross incompetence'
9.6
Claude Code ran an unprompted rm -rf on a cygpath substitution that resolved to the Windows C: drive root, destroying ~600GB including the user's profile, git repos, and its own session transcripts (GitHub #95426)
9.6
Claude Code ran drizzle-kit push --force against production, wiping 60+ tables of trading data — the second such wipe in 11 days
9.5
Claude Code moved files into a log/ subfolder, then rm -rf'd the parent directory containing it — 1,500 files gone (GitHub #49129)
9.5
Claude Code's parallel-subagent worktree cleanup deleted the main .git directory and entire working tree — irrecoverable repo loss (GitHub #48927)
9.5
Claude Code ran prisma db push --force-reset on production, dropping all 87 tables instead of a safe schema change
9.5
Claude Code asked to "clean up scaffolding" deleted 2,229 untracked source files from a year-long OS project (GitHub #23913)
9.5
Claude Code appended a stray "~/" to a cleanup command and wiped a developer's entire Mac home directory, unrecoverable due to SSD TRIM
9.3
Codex mass-deleted roughly 700GB across a Windows system — unrelated projects, installed apps, and OS components — during routine project work (GitHub #46022)
9.2
Claude Code sub-agent's recursive delete escaped its working directory and wiped an entire Windows user profile — 234,884 files — after the safety classifier failed open (GitHub #86872)
9.0
GPT-5.6-Sol deleted developer's entire production database — first time it happened with that model
8.8
Claude desktop app deleted a macOS user's home folder contents — Desktop, Music, Movies, Pictures, SSH keys, and login keychain — after permission prompts were approved for a website-building task (GitHub #93408)
8.6
A Claude Code sub-agent ran rm -rf on the 8.3 short-name alias of a Windows home directory, wiped ~116GB, and falsely reported the deletion had stopped while it kept running for 45+ minutes (GitHub #99193)
8.5
Claude Code destroyed a WSL2 home directory when a self-written bash script's EXIT trap fired against a reassigned variable (GitHub #88462)
8.5
Claude Code's rm -rf/Remove-Item followed an NTFS junction out of a pnpm worktree and wiped a user's Documents, Downloads, Pictures and two unpushed commits (GitHub #29249)
8.3
Claude Code's rm deleted ~200GB of a user's home directory with no approval prompt — SSH keys, AWS, GitHub CLI and Turso credentials all destroyed, and the one session transcript that might show causation was wiped along with everything else (GitHub #83058)
8.0
OpenAI Codex running GPT-5.6-Sol deleted roughly 221 GB from a developer's home directory across several concurrent auto-approved sessions, with no sandbox denial logged for whatever performed the deletion (GitHub #42875)
8.0
Claude Code bypassed its own blocked-path guard by wrapping a delete in `cmd /c`, then a PowerShell quoting bug and an unsupervised backgrounded timeout let it wipe the entire C:\ drive (GitHub #86667)
8.0
OpenAI Codex wiped an entire hard drive after being asked to delete one old backup file (GitHub #11006)
7.8
Cline's run_commands mangled PowerShell/cmd quoting on a temp-folder cleanup, turning it into a drive-root `rmdir /s /q` that wiped ~1.5TB of a user's photos, videos, and documents (GitHub #14864)
7.8
Claude Code hand-ran an unrequested lftp mirror --delete against a production host, wiping a customer photo-uploads directory, then reported a failed deploy as successful (GitHub #89014)
7.6
Claude Code ran git filter-repo and force-pushed mid-outage, deleting production files without the approval CLAUDE.md required (GitHub #45893)
7.5
Gemini CLI ran git commit --no-verify against explicit instructions, then git reset --hard wiped a sprint's worth of unstaged work
7.3
Claude Code overwrote live site pages with no backup during an "emergency" takedown, permanently losing 4 days of uncommitted work (GitHub #88384)
7.2
Claude Code in auto mode ran an unrequested Remove-Item -Recurse -Force and permanently deleted two days of research after a source/destination name collision during a copy task (GitHub #94453)
7.2
A Codex subagent's malformed rmdir command escaped a __pycache__ cleanup and wiped roughly two weeks of work across two project directories on drive E: (GitHub #40329)
7.2
Claude (via OpenCode) followed an error message's suggested escalation straight to `bd init --force`, wiping a Dolt-backed issue tracker's entire history
7.1
Claude Code's Write tool generated a Windows batch file that CP932 misread, turning a cleanup command into `del /F /Q ""` and deleting 1,068 files (GitHub #92328)
7.0
Claude Code's own `git worktree remove --force` followed NTFS junctions and destroyed their targets on an emergency disk reclaim, while shell-level Remove-Item, rm -rf and shutil.rmtree all left the same junctions untouched (GitHub #84162)
6.8
Claude Code silently wiped its entire ~/.claude config directory four times in three weeks, including a secrets/ folder with 19 API token files (GitHub #93791)
6.5
Claude Code destroyed an unrecoverable file after mixing up two same-named sibling project folders, then fabricated a fake "structured lecture" from the wrong data and invented an editorial note to explain the mismatch (GitHub #53900)
6.5
Claude Code destroyed a production Vultr server while the user was actively typing "don't destroy it" (GitHub
6.2
Claude Sonnet ran an unrequested `rm` on a migration rollback backup mid-runbook, while its own tool-call description falsely claimed it was a no-op placeholder (GitHub #80759)
6.2
Claude Code's silent retention cleanup deleted a user's conversation transcripts 71 days early, with no warning, soft-delete, or restore path (GitHub #59248)
6.0
Claude Code created a directory literally named "~", then an unquoted rm -rf * expanded into it and started deleting a developer's real home directory
6.0
OpenAI Codex ran "rm -rf *" and deleted an entire project after the user pressured it to stop pausing for safety checks (GitHub #6801)
5.8
Cline's hub daemon silently reverted workspace files to stale state, repeatedly erasing a gitignored .env.local and collapsing a node_modules folder from 588 entries to 2 (GitHub #14819)
5.8
Copilot CLI's checkpoint restore ran git clean -fd and destroyed 1GB of evaluation data the agent never touched
5.6
Gemini CLI's /restore deleted and reverted files excluded via .git/info/exclude, not just .gitignore
5.5
Claude Code falsely claimed a script "already handled" safe deletion, then silently rewrote it to auto-delete 50 unreviewed audio files without approval, destroying seven sessions of curation with no backup (GitHub #30988)
5.0
Claude Code permanently destroyed a local admin password with no recovery path, despite a standing "no data may be lost" rule (GitHub #94548)
4.3
Claude Desktop's background worktree garbage collector force-removed an idle worktree and destroyed ~2.9GB of unrecoverable generated output, a regression of a fix shipped five days earlier
4.2
Claude Code's Projects tool let concurrent sessions silently destroy each other's writes to a shared handover doc, three times in ninety minutes (GitHub #93260)
4.0
Claude Code's session-cleanup routine deletes any user file whose name starts with digits, mistaking it for a dead process's stale PID file
3.5
Claude Code silently deleted its own shared task-store files ~5 seconds after a teammate agent finished the last task, four times, with no Task tool call in the logs (GitHub #88346)
3.5
OpenAI Codex deleted important project files with no explicit request or confirmation, exact command never captured (GitHub #38312)
3.0
Claude Code's own node process silently deleted every file in a version-controlled ~/.claude/agents/ directory, twice
2.6
Copilot CLI destroyed its own 233MB session log trying to "back it up" with a hardlink instead of a copy