skills.rest
jerrylin96
jerrylin96COMMUNITY
Explore all skills by this author →
WebsiteGitHub

accidental-data-loss-prevention

Blocks irreversible deletion commands until explicit user consent is obtained.

9|Updated Jul 8, 2026
Search Tags:#sql#gcloud#data loss prevention#user consent#destructive commands#safety guardrail#deletion protection
One-click install
npx skills add https://github.com/jerrylin96/dotgemini --skill accidental-data-loss-prevention-jerrylin96
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: accidental-data-loss-prevention
Source: https://github.com/jerrylin96/dotgemini/tree/main/skills/accidental-data-loss-prevention
Command: npx skills add https://github.com/jerrylin96/dotgemini --skill accidental-data-loss-prevention-jerrylin96

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents can execute destructive commands like DROP TABLE, TRUNCATE, or gsutil rm without pausing, risking permanent loss of production data or critical infrastructure. This Skill enforces a mandatory stop-and-verify checkpoint before any irreversible operation runs. ## Core Features & Use Cases - Mandatory Consent Gate: Halts execution of any command causing irreversible data loss and requires explicit user approval before proceeding. - Broad Coverage of Destructive Operations: Covers SQL (DROP TABLE/VIEW/SCHEMA/DATABASE, TRUNCATE, unscoped DELETE), cloud storage deletion (gsutil rm, gcloud storage rm), and infrastructure teardown (project deletion, Spanner/BigQuery/Dataproc resource removal, secret deletion, KMS key destruction). - Use Case: When an agent proposes running gcloud projects delete or a DELETE statement without a WHERE clause, the Skill forces it to explain the impact, justify the action, and wait for affirmative confirmation instead of executing immediately. ## Quick Start Before running any destructive SQL, cloud storage, or infrastructure deletion command, stop and ask me for explicit confirmation first.

Frequently Asked Questions about accidental-data-loss-prevention

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent an AI agent from deleting production data?▼

Use a consent-gate instruction that forces the agent to halt before any irreversible command. The agent must explain the deletion impact, justify why it is needed, and wait for your explicit approval before executing.

What destructive SQL commands require confirmation before running?▼

DROP TABLE, DROP VIEW, DROP SCHEMA, DROP DATABASE, TRUNCATE, and broad DELETE statements missing a WHERE clause or using 1=1 all require confirmation. These operations permanently remove data with no rollback path.

Does this cover Google Cloud storage and infrastructure deletion?▼

Yes, it covers gsutil rm and gcloud storage rm against production buckets, plus gcloud projects delete, Spanner, BigQuery, and Dataproc resource deletion, secret deletion, and KMS key destruction.

What happens when the agent is unsure whether a command is destructive?▼

The default behavior is to ask rather than assume. The guidance states it is better to wait for confirmation than to accidentally delete production data or critical project assets.

Can the agent proceed without explicit user approval?▼

No. The mandatory procedure requires halting execution, requesting consent with a clear impact explanation, and proceeding only after the user gives clear affirmative confirmation in the conversation.

Related Skills

Explore More Software Engineering Skills→
DaBigHomieDaBigHomie
1

accidental-data-loss-prevention

Require explicit user confirmation before executing destructive SQL, cloud storage, or infrastructure commands.

Community
Intermediate
carson-sweetcarson-sweet
6

Purge SweetClaude

Remove SweetClaude configuration files and directories after user confirmation.

Community
Intermediate
AubreyHanAubreyHan

accidental-data-loss-prevention

Require explicit user consent before executing destructive SQL, cloud storage, and infrastructure operations.

Community
Basic
curpheycurphey

gcp

Identify IAM misconfigurations, insecure bindings, and risky service accounts in Google Cloud Platform deployments.

Community
Advanced