Опубликованные навыки 2
📦
skill-security
Audit AI Agent Skills Before Installation
Средний риск 71
Unvetted agent skills can hide prompt injection, credential theft, persistence, or unsafe dependencies. This skill combines offline scanning with guided semantic review.
Claude Codex Code(CC)
Установить📦
ci-cd-security
Audit GitHub Actions Workflows
Безопасно 75
GitHub Actions workflows can expose credentials, repositories, and releases through subtle configuration errors. This skill applies a structured security review and proposes concrete fixes.
Claude Codex Code(CC)
Установить