Volver a skills
opsecmd
por wulf715
iOS & macOS Development—Aún sin valoraciones
Tu valoración
Resumen
A swift reminder of both human and agent duties regarding operational security.
Descripción
Qué hace esta skill
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.
Cuándo usarla
- 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
Instalación
clawhub install wulf715/opsecmdEjecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.