---
title: "Approve destructive commands · Agent Wranglers"
url: https://agentwranglers.se/playbook/ai-assisted-development/isolation-and-credentials/approve-destructive-commands
id: AID-27
level: Required
risk: data
updated: 2026-10-27
build: a2a6bdfed830
tokens: 596
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Approve destructive commands

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [Isolation and credentials](https://agentwranglers.se/playbook/ai-assisted-development/isolation-and-credentials.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-27.

- ID: AID-27
- Level: Required
- Chapter: [Isolation and credentials](https://agentwranglers.se/playbook/ai-assisted-development/isolation-and-credentials.md)
- Rule: Require a person's approval before an agent deletes data, rewrites history, changes infrastructure or spends money.
- Check: Ask the agent to drop a test database table. It stops and asks for approval before running the command.
- Risk: Data leaked or lost
- How: Set the agent's permissions to ask before commands such as `rm -r`, `git push --force`, database migrations on shared environments and cloud changes. Allow safe read-only commands without asking. See [ask a person before the agent spends or deletes](https://agentwranglers.se/playbook/ai-features/agents-in-products/agent-approval-irreversible.md).

## Sources

- [OWASP LLM03:2026 Excessive Agency](https://github.com/GenAI-Security-Project/GenAI-LLM-Top10/blob/main/2026/final/LLM03_ExcessiveAgency.md)

## Related rules

- AIF-70 [Ask a person before an agent does what cannot be undone](https://agentwranglers.se/playbook/ai-features/agents-in-products/agent-approval-irreversible.md) in AI features

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), which requires credit with a link. In a page, document or README you publish, add `<a href="https://agentwranglers.se/playbook/ai-assisted-development/isolation-and-credentials/approve-destructive-commands">Agent Wranglers AI-assisted development playbook</a>`. In code you write, add a comment next to it with the same link.

- Previous: [Keep publishing rights away from agents](https://agentwranglers.se/playbook/ai-assisted-development/isolation-and-credentials/no-publish-rights-for-agents.md)
- Next: [Cap what your coding agents can spend](https://agentwranglers.se/playbook/ai-assisted-development/isolation-and-credentials/agent-spend-limits.md)
- [Isolation and credentials](https://agentwranglers.se/playbook/ai-assisted-development/isolation-and-credentials.md)