Quick overview
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.
Common tasks
- 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
Install paths
Primary command
openclaw install uchibeke/aport-agent-guardrail
ClawHub installer
npx clawhub@latest install uchibeke/aport-agent-guardrail
OpenClaw CLI
openclaw skills install uchibeke/aport-agent-guardrail
Direct OpenClaw install
openclaw install uchibeke/aport-agent-guardrail
Skill metadata
- Category: Coding Agents & IDEs
- Language: Markdown
- Version: 1.1.14
- Security status: Suspicious
Review upstream source
The full public SKILL.md body is not directly fetchable for this entry right now, so this page is using the best available catalog metadata. Review the upstream source page for the latest files, version history, and security scan details: https://clawhub.ai/uchibeke/aport-agent-guardrail
