Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

agent-safety

bởi compass-soul

Coding Agents & IDEs
475Lượt tải do clawskills.sh công bố
0Lượt xem
0 lượt thíchĐăng nhập để thích kỹ năng này
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Outbound safety for autonomous AI agents — scans YOUR output before it leaves the machine.

Mô tả

Kỹ năng này làm gì

Automated outbound safety for AI agents and developers. Scans files and staged git content for API keys, tokens, PII, and secrets before they leave the machine. Enforces security at the git level via pre-commit hooks, not prompts.

Unlike prompt-based reminders or inbound scanners, this enforces rules at the commit level so secrets are blocked automatically, not caught after the fact.

Khi nào nên dùng

  • Blocking accidental API key commits before they hit GitHub
  • Installing a one-time safety hook on a new repo
  • Scanning a directory before publishing a package
  • Checking for hardcoded emails or SSNs in generated files
  • Running a system health check during periodic agent maintenance

Quy trình ví dụ

ĐẦU VÀO

User asks: install the pre-commit hook on my repo at ~/projects/myapp

AGENT
  1. 1

    Resolve scripts/install-hook.sh path relative to the skill file

  2. 2

    Run: bash scripts/install-hook.sh ~/projects/myapp

  3. 3

    Confirm the hook is written to ~/projects/myapp/.git/hooks/pre-commit

  4. 4

    Report that future commits in that repo will be scanned automatically

ĐẦU RA

Pre-commit hook installed. Any staged secrets or SSNs will block the commit; PII patterns will flag for review.

Cài đặt

clawhub install compass-soul/agent-safety

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết