block-dangerous-commands
PreToolUse guard for Bash: blocks dangerous shell commands (rm -rf ~, fork bombs, curl|sh, force push to main) before they run, with three safety levels and opt-in per-level ask…
Paquete de plugins · de Karan Bansal
Resumen
block-dangerous-commands es un paquete de plugins para herramientas de programación con IA publicado por Karan Bansal. Marketplaces que leemos y que lo publican: 1 (Community GitHub marketplaces). El último cambio que registramos fue el 2026-10-26. Según nuestra pasada por los marketplaces del 2026-10-27.
PreToolUse guard for Bash: blocks dangerous shell commands (rm -rf ~, fork bombs, curl|sh, force push to main) before they run, with three safety levels and opt-in per-level ask mode.
Qué pide
- Se instala como paquete de plugins
- Hooks declarados: 1
Lo que declara, pide y ejecuta, completo
Instala solo plugins de desarrolladores en los que confíes. Mostramos lo que publican los marketplaces y no probamos plugins.
Funciona con
- Claude Code
Según los marketplaces que lo listan y el transporte MCP que declara, tal como lo documenta cada cliente. No probamos plugins.
Conectar
Comandos y configuraciones generados solo a partir de lo que declaran sus marketplaces. No los ejecutamos por ti ni probamos plugins.
Como plugin de Claude Code
Generado a partir de lo que declara Community GitHub marketplaces.
/plugin marketplace add karanb192/claude-code-hooks
/plugin install block-dangerous-commands@claude-code-hooksDónde está publicado
| Marketplace | Estado | Versión | Cifras | Verificado | Visto por primera vez |
|---|---|---|---|---|---|
| Marketplace de la comunidad karanb192/claude-code-hooks (Abrir el código en GitHub) | Publicado | 1.0.0 | Forks (GitHub): 48 Estrellas (GitHub): 563 |
Sin marca |
Cada cifra es del propio marketplace y nunca se suma entre marketplaces. Un marketplace que no publica cifras no muestra ninguna: sin número no es cero.
Figura en un marketplace de la comunidad
| Marketplace | Repositorio | Estrellas (GitHub) |
|---|---|---|
| claude-code-hooks | karanb192/claude-code-hooks | 563 |
Qué contiene el paquete
Tal como se publica en Community GitHub marketplaces.
Hooks: 1
PreToolUse
Qué cambió
- Pasó a ser un producto que seguimos
- Community GitHub marketplaces: apareció
Plugins similares
Productos cuyos propios nombres, descripciones, herramientas y skills son los más cercanos a este por su significado, en todos los marketplaces que leemos. La cercanía se ordena solo dentro de esta lista.
-
PreToolUse Bash guard for Claude Code that still holds under --dangerously-skip-permissions. Blocks pipe-to-shell installs, disk wipes and fork bombs; asks before rm -rf…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Block destructive git and filesystem commands before execution
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
Holds risky Bash commands and shows what they would change before they run.
-
Block destructive commands and secret access
-
Secrets firewall for tool calls: denies (or asks, per level) any Read/Edit/Write/Bash/Grep that would read, search, modify, or exfiltrate .env files, SSH keys, cloud credentials…
-
Safety guardrails for running Claude Code with reduced supervision. The guard-destructive PreToolUse hook matches against a normalized view of each command (heredoc bodies and…
Plugins similares por marketplace
La misma pregunta a cada marketplace por separado: ¿hay allí un equivalente de este plugin?
Publicado en Claude Code: claude-plugins-community (5)
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Block destructive git and filesystem commands before execution
-
DeployShield is a cross-platform production safety guardrail for Claude Code and Gemini CLI. It intercepts terminal commands before execution and blocks dangerous operations…
-
Auto-approve compound Bash commands (pipes, chains, subshells) by parsing each segment via shfmt AST and checking against allow/deny lists
-
PreToolUse hooks for Claude Code that deny dangerous shell, git, and credential commands before they run: `rm -rf /` shapes, `git push --force`, `python -c` / `node -e` eval…
Publicado en Claude Code: claude-plugins-official (5)
-
Semgrep catches security vulnerabilities in real-time and guides Claude to write secure code from the start.
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
Preset CLI skills for explicit shell, scripting, and CI/CD workflows driven by the `sup` CLI (PyPI package `superset-sup`). Use only for CLI workflows; do not use for MCP-only…
-
Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the…
Publicado en Claude: knowledge-work-plugins (5)
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into…
-
MCP server for terminal commands, file operations, and process management
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
Publicado en Codex: openai-curated (openai/plugins) (5)
-
Codex Security workflows for security scans, analysis, and investigation.
-
Inspect repositories, triage pull requests and issues, debug CI, and publish changes through a hybrid GitHub connector and CLI workflow.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
Publicado en Community GitHub marketplaces (4)
-
PreToolUse Bash guard for Claude Code that still holds under --dangerously-skip-permissions. Blocks pipe-to-shell installs, disk wipes and fork bombs; asks before rm -rf…
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-closed design.
-
Holds risky Bash commands and shows what they would change before they run.
-
Block destructive commands and secret access
Publicado en Copilot CLI: github/awesome-copilot (5)
-
GitHub Security canvas for Copilot. Review your session's changes for vulnerabilities and fix code scanning alerts.
-
Triage Dependabot alerts and recommend safe, evidence-based dependency updates.
-
Use an installed rhost CLI to run ordinary commands on SSH-reachable Linux hosts with local-like stdin, output, and exit behavior.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Automatically enforce SonarQube code quality and security in the agent coding loop — 7,000+ rules, secrets scanning, agentic analysis, and quality gates across 40+ languages…
Publicado en Copilot CLI: github/copilot-plugins (5)
-
Advanced Security plugin for GitHub Copilot.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
Microsoft Dataverse plugin for coding agents, covering record CRUD, bulk data operations, advanced queries, schema and metadata, administration, security, environment management…
Publicado en Cursor: cursor/plugins (5)
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Scaffold and validate new agent plugins.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Build apps, scripts, and automations with the TypeScript SDK.
-
Internal team workflows for CI, code review, shipping, local automation, and verification.
Publicado en Docker MCP Catalog (5)
-
MCP server for terminal commands, file operations, and process management
-
MCP server for using Semgrep to scan code for security vulnerabilities.
-
A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
-
npm-sentinel-mcp io.github.Nekzus/npm-sentinel-mcp
Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
-
Giving Claude ability to run code with E2B via MCP (Model Context Protocol).
Publicado en Official MCP Registry (5)
-
shellward io.github.jnMetaCode/shellward
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
-
bash-vet-mcp io.github.temurkhan13/bash-vet-mcp
Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.
-
Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
GuardianShield io.github.sparkvibe-io/GuardianShield
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
Publicado en PyPI (MCP servers) (5)
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
-
e2b com.mcparmory/e2b
Create and manage secure sandboxes for running AI agent code
-
Every tool your AI needs in one self-hosted install: memory, reasoning, git, Docker and more.
-
Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
Publicado en npm registry (MCP servers) (5)
-
speclock io.github.sgroy10/speclock
AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.
-
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
-
guardvibe io.github.goklab/guardvibe
Deterministic security layer your AI can't be. 624 rules, 39 tools, CLI + doctor + host audit.
-
mcp-ssh-manager io.github.bvisible/mcp-ssh-manager
SSH for AI agents: commands, files, backups and health, with approval, a vault and an audit trail
-
git-mcp-server io.github.cyanheads/git-mcp-server
Comprehensive Git MCP server enabling native git tools including clone, commit, worktree, & more.
Encontrados por significado, no por código ni repositorio compartidos: los plugins similares siguen siendo productos distintos, y esto no es una reseña ni una recomendación.
¿Quieres esta marca para tu plugin en nuestro catálogo?
Demuestra que lo mantienes con un archivo en su repositorio, un archivo en tu dominio o un registro DNS, y podrás mostrar esta marca en la ficha, con banners en vivo para tu web y tu README. Cómo funciona la verificación
Además recibirás avisos cuando un marketplace lo publique, lo retire, cambie su marca verificada o lo que pide, y su endpoint remoto quedará monitorizado como un servicio web.
Datos de Community GitHub marketplaces. Las cifras proceden de nuestros propios recorridos periódicos por los marketplaces, leída por última vez el . No publicamos datos de contacto de los editores de plugins.