Перейти к содержимому
TakoAPI
Назад к навыкам

antivirus

от thomaslwang

Coding Agents & IDEs
1.7kЧисло загрузок по данным clawskills.sh
1Звёзды
0Просмотры
0 лайковВойдите, чтобы поставить лайк навыку
—Ещё нет оценок
Ваша оценка

Кратко

Scan installed OpenClaw skills for malicious code patterns including ClickFix social engineering, reverse shell (RAT)

Описание

Что делает этот навык

MoltGuard is a security plugin for OpenClaw agents that detects prompt injection attacks, data exfiltration attempts, and malicious commands hidden in files and web content. It analyzes three risk surfaces: prompt and instruction content, agent behavior, and data exposure. Installation is automatic and a free tier provides 500 detections per day.

It intercepts threats at the agent execution layer, catching injected instructions in external files and web content before the agent acts on them.

Когда его использовать

  • Blocking hidden prompt injection attacks in email attachments
  • Preventing credential leakage before sensitive data leaves the agent
  • Catching malicious file deletion commands embedded in web content
  • Stopping PII from being sent to external LLMs
  • Detecting unauthorized API calls triggered by injected instructions

Пример сценария

ВВОД

User asks: Read and summarize this email attachment

АГЕНТ
  1. 1

    Agent reads the email file

  2. 2

    MoltGuard sends the content to Core for risk analysis

  3. 3

    Core detects a hidden prompt injection instruction inside the email body

  4. 4

    MoltGuard blocks the injected instruction from executing

  5. 5

    Agent reports the detected attack back to the user

ВЫВОД

User is alerted to the injection attempt; the malicious instruction is not followed

Установка

clawhub install thomaslwang/antivirus

Выполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.

Ссылки