TAG · 2 prompts

#安全

Explore public prompts for 安全. Narrow the topic by medium or change the order.

Showing 1–2 of 2 · Page 1 / 1

TUTORIALClaude Code

Karan Bansal2026-06-08

Claude Code Hook Recipe: Block Dangerous Bash with PreToolUse

A PreToolUse Bash hook that intercepts destructive commands like rm -rf, fork bombs, and curl|sh before the AI executes them—a last line of defense that holds even against --dangerously-skip-permissions.

Intermediate

Read

Free02

TUTORIALOpenAI Codex

RoggeOhta2026-06-08

Codex config.toml in Practice: Approval Modes × Sandbox Isolation × Profiles

A ready-to-paste ~/.codex/config.toml template that sets up OpenAI Codex CLI's approval policy, sandbox isolation, reasoning effort, and multiple profiles in one go — balancing automation efficiency with safety boundaries.

Intermediate

Read