Saltar al contenido
TakoAPI
Volver a skills

vigil

por robinoppenstam

Git & GitHub
729Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

AI agent safety guardrails for tool calls.

Descripción

Qué hace esta skill

Vigil validates AI agent tool calls before they execute, blocking operations like destructive shell commands, SSRF, SQL injection, path traversal, and credential leaks. It runs as a drop-in npm package with 22 rules, zero runtime dependencies, and under 2ms latency per check.

Zero runtime dependencies and sub-2ms latency mean it can run inline on every tool call without adding measurable overhead to the agent pipeline.

Cuándo usarla

  • Blocking rm -rf commands issued by autonomous agents
  • Preventing SSRF in agent-driven API and HTTP calls
  • Catching SQL injection before a database tool executes
  • Auditing all tool calls made by a shell-executing agent
  • Adding a safety layer to an existing MCP server

Flujo de trabajo de ejemplo

ENTRADA

User asks: validate a shell command before my agent runs it

AGENTE
  1. 1

    Import checkAction from vigil-agent-safety

  2. 2

    Pass the tool name and params object to checkAction

  3. 3

    Receive a decision (ALLOW, BLOCK, or ESCALATE) with a reason string

  4. 4

    Block execution or proceed based on the returned decision

SALIDA

BLOCK: Destructive command pattern — the rm -rf / call is rejected before execution

Requisitos

  • vigil-agent-safety npm package

Instalación

clawhub install robinoppenstam/vigil

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces