What is dangerous-bash-guard?

A safety hook that checks Bash commands before they run. It blocks commands that can permanently damage files or systems and asks for confirmation before risky shared or Git operations.

It is for guarding commands such as recursive deletion, disk formatting, force-pushing, hard resets, pull-request changes, Kubernetes operations, Terraform changes, and cloud or Docker deletion.

It reduces the chance that an automated agent will erase data, rewrite project history, change cloud resources, or affect shared environments without approval.

dangerous-bash-guard — Plugin for Claude Code by thapr0digy/skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/thapr0digy/skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/thapr0digy/skills/dangerous-bash-guard/github.svg)](https://agentmods.dev/plugins/thapr0digy/skills/dangerous-bash-guard)

Your own site

<a href="https://agentmods.dev/plugins/thapr0digy/skills/dangerous-bash-guard"><img src="https://agentmods.dev/badge/plugins/thapr0digy/skills/dangerous-bash-guard/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/thapr0digy/skills/dangerous-bash-guard"><img src="https://agentmods.dev/badge/plugins/thapr0digy/skills/dangerous-bash-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade D, and why

dangerous-bash-guard scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

"description": "PreToolUse hook that hard-blocks irreversible filesystem and system-destructive Bash commands (rm -rf /, dd to /dev/*, mkfs, fork bombs, sudo destructives) and prompts via permissionDecision: ask for hist

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"description": "PreToolUse hook that hard-blocks irreversible filesystem and system-destructive Bash commands (rm -rf /, dd to /dev/*, mkfs, fork bombs, sudo destructives) and prompts via permissionDecision: ask for hist

plugins/dangerous-bash-guard/.claude-plugin/plugin.json · 9 lines

What it actually says

{
  "name": "dangerous-bash-guard",
  "version": "0.1.0",
  "description": "PreToolUse hook that hard-blocks irreversible filesystem and system-destructive Bash commands (rm -rf /, dd to /dev/*, mkfs, fork bombs, sudo destructives) and prompts via permissionDecision: ask for history-rewriting and shared-state side effects (git force-push/reset --hard/filter-repo, gh pr merge/close, kubectl delete/apply, terraform apply/destroy, aws delete-* / s3 rb / s3 rm --recursive, docker volume rm). Designed for use under bypassPermissions mode to retain a one-keypress safety gate. Escape hatch: prefix with CLAUDE_ALLOW_DANGEROUS=1 (audit-logged to ~/.claude/dangerous-overrides.log).",
  "author": {
    "name": "thapr0digy"
  }
}

Contents

What it installs

The manifest is a name and a version. 1 hook travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.

Hook PreToolUse A not measured

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 9 lines scan D 91f5cf1e81b4

Subscribe to this mod's changes

dangerous-bash-guard is a plugin published in the GitHub repository thapr0digy/skills (2 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.