कंटेंट पर जाएँ
TakoAPI
स्किल्स पर वापस

apoer-agent-guardrail

uchibeke द्वारा

Coding Agents & IDEs
—अभी तक कोई रेटिंग नहीं
आपकी रेटिंग

संक्षिप्त

Pre-action authorization for AI agents.

विवरण

यह स्किल क्या करती है

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.

इसे कब इस्तेमाल करें

  • 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

उदाहरण वर्कफ़्लो

इनपुट

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

एजेंट
  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

आउटपुट

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

आवश्यकताएँ

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

इंस्टॉलेशन

clawhub install uchibeke/apoer-agent-guardrail

CLI कमांड चलाएँ, या प्रॉम्प्ट को Claude Code, Cursor, Codex या जो भी कोडिंग एजेंट आप इस्तेमाल करते हैं उसमें पेस्ट करें।

लिंक