본문으로 건너뛰기
TakoAPI
스킬로 돌아가기

agentgate-security

wiserautomation 제작

Coding Agents & IDEs
357clawskills.sh가 보고한 다운로드 수
1조회수
좋아요 0개로그인하면 이 스킬에 좋아요를 누를 수 있습니다
—아직 평가 없음
내 평가

요약

displayName: AgentGate - Enterprise Security Firewall for OpenClaw.

설명

이 스킬이 하는 일

AgentGate is a middleware layer that intercepts every tool call an OpenClaw agent makes before it executes. It evaluates each call against regex-based policies stored in Firestore and returns ALLOW, DENY, or REQUIRE_APPROVAL. Blocked actions return a structured error; approvals pause execution until an operator responds.

Policies are enforced before tool execution, so a hallucinating agent cannot bypass rules by retrying or rephrasing the same call.

사용 시점

  • Blocking destructive bash commands like rm -rf in automated agent pipelines
  • Requiring human approval before Stripe charges exceed a set dollar threshold
  • Restricting outbound HTTP requests to a whitelist of approved domains
  • Auditing every agent tool call in real time with a live Firestore log
  • Preventing agents from sending unauthorized emails via SMTP or SendGrid

예시 워크플로

입력

User asks: Process a $500 refund for customer order #9821

에이전트
  1. 1

    Agent invokes the stripe tool with a charge amount of 50000

  2. 2

    AgentGate intercepts the call and POSTs the tool name and serialized arguments to the Firebase Cloud Function

  3. 3

    Function validates the API key, evaluates regex policies, and matches the amount against the approval threshold rule

  4. 4

    Decision is REQUIRE_APPROVAL; a Telegram webhook fires to the operator with Approve/Deny buttons

  5. 5

    Operator approves; Firestore updates and the agent resumes execution

출력

Stripe refund completes after human approval, with the full interaction recorded in the audit log

요구 사항

  • AgentGate account at agent-gate-rho.vercel.app
  • AGENTGATE_API_KEY environment variable

설치

clawhub install wiserautomation/agentgate-security

CLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.

링크