Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

vigil

bởi robinoppenstam

Git & GitHub
729Lượt 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

AI agent safety guardrails for tool calls.

Mô tả

Kỹ năng này làm gì

Vigil validates AI agent tool calls before they execute, blocking operations like destructive shell commands, SSRF, SQL injection, path traversal, and credential leaks. It runs as a drop-in npm package with 22 rules, zero runtime dependencies, and under 2ms latency per check.

Zero runtime dependencies and sub-2ms latency mean it can run inline on every tool call without adding measurable overhead to the agent pipeline.

Khi nào nên dùng

  • Blocking rm -rf commands issued by autonomous agents
  • Preventing SSRF in agent-driven API and HTTP calls
  • Catching SQL injection before a database tool executes
  • Auditing all tool calls made by a shell-executing agent
  • Adding a safety layer to an existing MCP server

Quy trình ví dụ

ĐẦU VÀO

User asks: validate a shell command before my agent runs it

AGENT
  1. 1

    Import checkAction from vigil-agent-safety

  2. 2

    Pass the tool name and params object to checkAction

  3. 3

    Receive a decision (ALLOW, BLOCK, or ESCALATE) with a reason string

  4. 4

    Block execution or proceed based on the returned decision

ĐẦU RA

BLOCK: Destructive command pattern — the rm -rf / call is rejected before execution

Yêu cầu

  • vigil-agent-safety npm package

Cài đặt

clawhub install robinoppenstam/vigil

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

Liên kết