What is bash-safety-guard?

A command-line safety guard for Claude Code, Anthropic's coding assistant. It checks shell commands before they run and blocks destructive production-data actions, credential leaks, and dangerous recursive deletion.

Use it as a pre-command protection layer for database, cloud-storage, cache, credential, and filesystem operations run through Bash.

It reduces the chance that an agent or developer will erase live data, expose secrets, or delete an important directory through a shell command.

bash-safety-guard — Plugin by ooiyeefei

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.

Claude Code

/plugin marketplace add ooiyeefei/ccc

agentmods

npx agentmods add plugins/ooiyeefei/ccc/bash-safety-guard

Clone the repo

git clone --depth 1 https://github.com/ooiyeefei/ccc

Made for: Claude Code.

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 C 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade C, and why

bash-safety-guard scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

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

"description": "Fail-closed PreToolUse bash guard for Claude Code: blocks destructive production-data operations (DROP/TRUNCATE/DELETE FROM, convex import --replace/--prod, prisma/drizzle reset, redis flush, dynamo/S3 de

plugins/bash-safety-guard/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "bash-safety-guard",
  "version": "1.0.0",
  "description": "Fail-closed PreToolUse bash guard for Claude Code: blocks destructive production-data operations (DROP/TRUNCATE/DELETE FROM, convex import --replace/--prod, prisma/drizzle reset, redis flush, dynamo/S3 deletes), credential exfiltration (secret files/tokens sent off-box or piped to paste/tunnel sinks), and catastrophic rm -rf (/, ~, $HOME, ., system dirs). Non-bash tools are untouched.",
  "author": {
    "name": "ooiyeefei"
  },
  "keywords": ["security", "guardrail", "safety", "hooks", "pretooluse", "bash", "fail-closed"]
}

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.

2d ago First seen · 10 lines scan C 06fcc1cce127

Subscribe to this mod's changes

bash-safety-guard is a plugin published in the GitHub repository ooiyeefei/ccc (483 stars, last pushed 1mo 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 C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Databases Security

bash-safety-guard

Getting it into your agent

Grade C, and why

Recursive force deletehighDestructive command

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc

ecc