skill-security-review
Review the security of an OpenClaw skill or agent before installation, import, activation, or trust. Use when the user asks whether a skill is safe, asks to review a .skill package, asks whether a GitHub/ClawHub/zip-based skill is safe, or expresses intent to install/import/enable a skill. Default behavior: if the user wants to install a skill, audit first, then present the verdict and ask for confirmation before installing. Focus on data exposure, local command execution, persistence, network a