mailbox-botPostal mail API for AI agents: send physical mail, use inbound context, and join the launching-soon mailbox address beta (street + mailbox number).
Install via ClawdBot CLI:
clawdbot install arbengine/mailbox-botGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://mailbox.bot/api/v1/waitlistCalls external URL not in known-safe list
https://github.com/arbengine/mailbox-bot-skillAI Analysis
The skill's external API calls (waitlist submission, GitHub repository) appear consistent with its stated purpose of providing a logistics service and are not inherently malicious. However, the undocumented POST endpoint to mailbox.bot for a waitlist could collect user data without clear disclosure, representing a minor privacy concern.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
An AI agent orders electronic components, sensors, or networking gear from suppliers like Amazon or distributors, using the warehouse address for delivery. Upon arrival, packages are scanned and webhook notifications trigger the agent to update inventory, schedule assembly, or forward items to production sites, enabling hands-free supply chain management.
Legal or financial AI agents receive physical contracts, filings, or sensitive documents via private couriers like FedEx or DHL to the warehouse address. Each document is scanned and photographed upon arrival, with structured data sent via webhook, allowing the agent to automatically categorize, archive, or route for digital processing without manual handling.
Agents managing edge computing or field devices use the warehouse to receive servers, sensors, and networking equipment from carriers like UPS. The agent receives instant notifications with photos and metadata, then autonomously requests forwarding to deployment locations or schedules on-site installation, streamlining remote infrastructure setup.
E-commerce AI agents set the warehouse as a return destination for customer RMAs, accepting returns from private carriers like DHL or Amazon. Returns are automatically scanned and routed back to the agent via reference codes, enabling the agent to process refunds, restock inventory, or initiate repairs without human intervention.
Operations agents monitor stock levels and autonomously reorder supplies when low, shipping items to the warehouse address. Upon arrival, webhook data triggers the agent to forward packages to end destinations like offices or warehouses, optimizing inventory replenishment and distribution with minimal oversight.
Charge users a monthly or annual subscription fee for access to the API, with tiered plans based on features like package volume, storage duration, or forwarding frequency. Revenue is generated from recurring payments, appealing to businesses with ongoing logistics needs for their AI agents.
Implement a usage-based pricing model where customers pay per package received, scanned, or forwarded, with additional fees for services like high-res photos or extended storage. This model scales with customer activity, generating revenue directly from operational logistics actions performed by agents.
Offer premium enterprise packages that include custom integrations, dedicated support, and enhanced security features like KYC verification via Stripe Identity. Revenue comes from one-time setup fees and ongoing support contracts, targeting large organizations with complex agent-driven logistics requirements.
💬 Integration Tip
Start by setting the MAILBOX_BOT_API_KEY environment variable and test with the waitlist endpoint to ensure connectivity before integrating authenticated API calls for package management.
Scored Jun 19, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...