Saltar al contenido
TakoAPI
Volver a skills

skillsentry

por poolguy24

Coding Agents & IDEs
790Descargas según clawskills.sh
0Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

OpenClaw security audit + prompt injection detector.

Descripción

Qué hace esta skill

Audits a local OpenClaw install for security vulnerabilities and prompt-injection indicators. Scans gateway configurations, open ports, and known injection patterns, then outputs a JSON report. Can be scheduled to run on a recurring cadence via cron.

Combines OpenClaw-specific prompt-injection detection with general vulnerability scanning in one tool, which generic security scripts don't provide.

Cuándo usarla

  • Auditing an OpenClaw install after adding new skills
  • Detecting prompt-injection patterns in agent interactions
  • Scheduling daily automated security checks via cron
  • Identifying unexpected open ports on a local setup
  • Reviewing security posture before sharing or deploying an install

Flujo de trabajo de ejemplo

ENTRADA

User asks: Run a security audit on my OpenClaw install

AGENTE
  1. 1

    Launch the panel server with node scripts/panel-server.js

  2. 2

    Open the scan UI at http://localhost:8133

  3. 3

    Run bash scripts/audit.sh to execute the audit

  4. 4

    Review JSON output for prompt-injection hits or unexpected open ports

SALIDA

JSON report listing detected vulnerabilities, open ports, and any prompt-injection pattern matches, stored at logs/last-report.json

Instalación

clawhub install poolguy24/skillsentry

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

Enlaces