本文へスキップ
TakoAPI
スキル一覧に戻る

antivirus

thomaslwang 作

Coding Agents & IDEs
1.7kダウンロード数はclawskills.shが公開している値です
1スター
0閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

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

説明

このスキルでできること

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.

使いどころ

  • 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

ワークフロー例

入力

User asks: Read and summarize this email attachment

エージェント
  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

出力

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

インストール

clawhub install thomaslwang/antivirus

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク