Bartholomew Guard: shipping an AI safety gate for destructive actions

Описание и применение

Bartholomew Guard – это слой безопасности, который блокирует опасные команды, генерируемые ИИ, в среде разработки и CI, предоставляя объяснения и аудит.

Задача

AI agents can issue destructive or high‑risk commands that bypass normal safety checks, leading to accidental data loss or system compromise.

Результат

Implemented a practical safety layer that blocks unsafe AI‑generated shell commands, provides clear explanations, and logs decisions for auditability, enhancing developer confidence in AI‑assisted workflows.

Рабочий процесс

• 1. Install Bartholomew Guard as a VS Code extension or GitHub Action.
• 2. When an AI agent proposes a shell command, the guard evaluates intent and pattern matching.
• 3. If the command is flagged as destructive, the guard blocks execution and returns a denial message.
• 4. The decision is logged in a receipt‑style record for audit.
• 5. Developers continue the workflow with safe commands.
• 6. Review logs to understand denied actions and adjust policies if needed.

Доказательства

We built Bartholomew to stop unsafe AI-driven commands before they execute.

Источник

The guard evaluates command intent, flags destructive patterns, and denies actions like shell deletion, risky file operations, and unsafe execution paths.

Источник