Home/ Incident database/claude-code-issue-10077-2025-10
Data breach Data loss verified

Claude Code recursive delete runs with the permission system on; home directory unrecoverable

Anthropic (Claude Code) · Oct 21, 2025 · Coding agent

What happened

Developer Mike Wolak filed GitHub issue #10077 after Claude Code executed a recursive delete starting from root on his Ubuntu/WSL2 system, destroying every user-owned file. He was not running --dangerously-skip-permissions; the permission system was active and did not detect that the command would expand destructively before he approved it. Anthropic tagged the report as a security bug; nothing was recovered.

Loss / impact
Oct 21
2025
Data
Failure mode
Coding
Agent type

Causal vector

Permission prompt approved a command whose shell expansion deleted far more than presented; no deny rule matched the expansion

Source

Reported by GitHub issue, anthropics/claude-code #10077. Verified against the primary report.

Read the original report ↗

How a spend firewall would have helped

The permission prompt showed a command, not its blast radius. sipi.bot classifies recursive-delete-class operations as high-risk categories that are FLAGGED for human review with rate-limited execution, so an approved 'cleanup' cannot expand into an unrecoverable wipe at machine speed.

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

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. 95 documented failures, one control.