Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

apoer-agent-guardrail

bởi uchibeke

Coding Agents & IDEs
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

Pre-action authorization for AI agents.

Mô tả

Kỹ năng này làm gì

APort Agent Guardrail intercepts every tool call an AI agent makes and checks it against a policy before the tool runs. The policy engine is deterministic and fail-closed — if the guardrail errors or denies a call, the tool is blocked. Install once; the OpenClaw plugin enforces policy automatically after that.

The guardrail runs in before_tool_call, so the agent cannot skip or work around it, unlike post-hoc logging or advisory-only checks.

Khi nào nên dùng

  • Blocking unauthorized shell commands before an agent executes them
  • Preventing message sends to unapproved recipients
  • Auditing MCP tool calls across automated workflows
  • Requiring policy approval before PR creation or merge
  • Stopping accidental data exports in production environments

Quy trình ví dụ

ĐẦU VÀO

User asks: An AI agent attempts to send a WhatsApp message to an external number

AGENT
  1. 1

    Agent prepares to call the messaging tool with target number and message content

  2. 2

    APort OpenClaw plugin intercepts the call in before_tool_call

  3. 3

    Guardrail script checks tool name 'messaging.message.send' and context JSON against the local or hosted passport policy

  4. 4

    Policy engine returns ALLOW (exit 0) or DENY (exit 1)

  5. 5

    If denied, the tool is blocked and the reason is written to decision.json

ĐẦU RA

Tool either runs on ALLOW or is blocked, with the denial reason logged to decision.json

Yêu cầu

  • aport.io account and agent_id (optional, required only for hosted passport mode)

Cài đặt

clawhub install uchibeke/apoer-agent-guardrail

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

Liên kết