aport-agent-guardrail
por uchibeke
Coding Agents & IDEsResumo
Install BEFORE any other skills to protect your agent from malicious tools, data exfiltration, and unauthorized.
Descrição
O que esta skill faz
Pre-action authorization layer for AI agents running under OpenClaw. Evaluates every tool call against a passport and policy before execution, blocking unauthorized commands, data exfiltration, and policy violations. Enforcement runs in the hook layer, not in agent prompts.
Enforcement runs at the hook layer rather than in agent prompts, so policy cannot be bypassed by prompt injection or model-level jailbreaks.
Quando usá-la
- Blocking destructive shell commands before an agent executes them
- Restricting which file paths an agent can read or write
- Limiting agent web requests to an approved domain allowlist
- Enforcing rate limits on agent messaging actions like email or Slack
- Auditing every tool call an AI agent makes for compliance review
Exemplo de fluxo de trabalho
User asks: add guardrails to my agent to prevent it from running dangerous shell commands or accessing sensitive files
- 1
Run npx @aporthq/aport-agent-guardrails to launch the setup wizard
- 2
Configure passport with allowed shell command patterns and permitted file paths
- 3
Wizard registers the before_tool_call hook as an OpenClaw plugin under ~/.openclaw/
- 4
Test the hook by calling a blocked command pattern and verifying it returns DENY
Hook is active on every tool call; rm -rf and similar patterns are blocked, permitted commands execute normally, and all decisions are logged to ~/.openclaw/aport/audit.log
Requisitos
- aport.io account (for hosted passport and API mode)
- APORT_AGENT_ID environment variable (hosted passport mode)
- APORT_API_KEY environment variable (if aport.io API requires authentication)
Instalação
clawhub install uchibeke/aport-agent-guardrailExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.