agentgate-security
wiserautomation 作
Coding Agents & IDEs概要
displayName: AgentGate - Enterprise Security Firewall for OpenClaw.
説明
このスキルでできること
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.
使いどころ
- 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
ワークフロー例
User asks: Process a $500 refund for customer order #9821
- 1
Agent invokes the stripe tool with a charge amount of 50000
- 2
AgentGate intercepts the call and POSTs the tool name and serialized arguments to the Firebase Cloud Function
- 3
Function validates the API key, evaluates regex policies, and matches the amount against the approval threshold rule
- 4
Decision is REQUIRE_APPROVAL; a Telegram webhook fires to the operator with Approve/Deny buttons
- 5
Operator approves; Firestore updates and the agent resumes execution
Stripe refund completes after human approval, with the full interaction recorded in the audit log
要件
- AgentGate account at agent-gate-rho.vercel.app
- AGENTGATE_API_KEY environment variable
インストール
clawhub install wiserautomation/agentgate-securityCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。