Zurück zu den Skills
opsecmd
von wulf715
iOS & macOS Development—Noch nicht bewertet
Deine Bewertung
Kurzbeschreibung
A swift reminder of both human and agent duties regarding operational security.
Beschreibung
Was dieser Skill macht
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.
Wann du ihn einsetzt
- 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
Installation
clawhub install wulf715/opsecmdFühre den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.