Saltar al contenido
TakoAPI
Volver a skills

agent-hardening

por x1xhlol

CLI Utilities
649Descargas según clawskills.sh
4Estrellas
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Test your agent's input sanitization against common injection attacks.

Descripción

Qué hace esta skill

Runs self-contained security checks on OpenClaw agents to test input sanitization. Covers unicode control character stripping, HTML comment injection detection, and bidi override character identification. Uses only hardcoded synthetic samples — no local files or external connections.

Requires nothing beyond Python 3, so checks run immediately with no setup, accounts, or network access.

Cuándo usarla

  • Verify an agent strips zero-width unicode characters before processing user input
  • Detect hidden HTML directives injected into agent context windows
  • Check if filename spoofing via bidi override characters is caught
  • Run a quick pre-deployment security audit on a new agent
  • Validate input sanitization logic during agent development

Flujo de trabajo de ejemplo

ENTRADA

User asks: run the agent hardening checks on my agent

AGENTE
  1. 1

    Runs unicode control character sanitization test against synthetic samples

  2. 2

    Runs HTML comment injection detection against sample strings

  3. 3

    Runs bidi override detection against sample filenames

  4. 4

    Reports pass/fail counts for each check category

SALIDA

Summary showing how many checks passed per category, with flagged samples highlighted

Instalación

clawhub install x1xhlol/agent-hardening

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

Enlaces