スキル一覧に戻る
opsecmd
wulf715 作
iOS & macOS Development—まだ評価がありません
あなたの評価
概要
A swift reminder of both human and agent duties regarding operational security.
説明
このスキルでできること
A non-executable OPSEC reminder document for both humans and AI agents. Covers basic due diligence around reviewing and trusting scripts before execution in agentic systems. Written in response to observed abuse of agent trust to cause real harm via malicious skill files.
Addresses the specific attack surface of malicious skill files in agentic systems, a gap that general security checklists do not cover.
使いどころ
- Reviewing a third-party skill file before letting an agent execute it
- Spot-checking automated scripts in an agentic pipeline before deployment
- Onboarding team members to baseline OPSEC practices for AI agent setups
- Deciding whether to trust a downloaded script when its behavior is unclear
- Establishing a human-readable policy for agents running with minimal supervision
インストール
clawhub install wulf715/opsecmdCLI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。