Kembali ke skill
opsecmd
oleh wulf715
iOS & macOS Development—Belum ada penilaian
Penilaian Anda
Ringkasan
A swift reminder of both human and agent duties regarding operational security.
Deskripsi
Apa yang Dilakukan Skill Ini
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.
Kapan Menggunakannya
- 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
Instalasi
clawhub install wulf715/opsecmdJalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.