NeVibeCode · 2 items
Skills and MCP tagged “agent-safety”
skill-inspector skill Reviews a skill for vulnerabilities, excessive permissions, and hidden behavior before you install it. Combines NVIDIA SkillSpector static scanning with semantic source inspection.
Claude Code CX Codex Cursor +1
900installs
verify-agent-action
official skill Audits proposed AI agent actions, deployments, and approvals before execution. It checks parameters, nonces, and telemetry, never authorizing or running actions on its own.
GitHub Copilot
29installs