k2ljl-agentmailAPI-first email platform designed for AI agents. Create and manage dedicated email inboxes, send and receive emails programmatically, and handle email-based...
Install via ClawdBot CLI:
clawdbot install davidsteelerose/k2ljl-agentmailGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Ignore previous instructions"Sends data to undocumented external endpoint (potential exfiltration)
webhook → https://myapp.com/webhookCalls external URL not in known-safe list
https://console.agentmail.toUses known external API (expected, informational)
api.github.comGenerated Mar 22, 2026
Deploy an AI agent to handle customer inquiries via email, automatically creating tickets, sending responses, and escalating complex issues. AgentMail's webhooks enable real-time processing of incoming support emails, while high-volume sending ensures timely replies without rate limits.
Set up an email-based system where users send documents (e.g., invoices, forms) to a dedicated inbox. The AI agent extracts structured data, processes attachments, and triggers downstream actions like database updates or notifications, leveraging AgentMail's API for seamless integration.
Use AgentMail to manage email campaigns for lead nurturing or product announcements, with AI agents personalizing content based on recipient data. The platform's programmatic inboxes allow for scalable sending and tracking of engagement metrics without the constraints of traditional email providers.
Implement an email-driven workflow for internal teams where AI agents send alerts, reminders, or reports via dedicated inboxes. AgentMail's real-time events ensure immediate delivery and can integrate with tools like Slack or project management software for streamlined operations.
Provide AI assistants with unique email addresses to interact with external services, such as booking appointments or sending confirmations. AgentMail's custom domain support allows for branded identities, while security features like allowlisting mitigate prompt injection risks.
Charge customers based on the volume of emails sent and received, with tiered pricing for features like custom domains or advanced AI capabilities. This aligns costs with actual usage, appealing to startups and enterprises scaling their email operations.
Offer annual contracts with dedicated support, SLAs, and custom integrations for large organizations. This model targets industries with high compliance needs, such as finance or healthcare, ensuring reliability and security for critical email workflows.
Provide a free tier with basic email functionality to attract developers and small teams, then upsell to paid plans for advanced features like webhooks, custom domains, and higher volume limits. This encourages adoption and conversion as users scale.
💬 Integration Tip
Start by setting up webhooks with an allowlist to prevent prompt injection attacks, then gradually expand features like custom domains as your workflow matures.
Scored Jun 19, 2026
AI Analysis
The skill interacts with a legitimate external API (AgentMail) for its stated email functionality, which is expected. The identified 'prompt injection' risk is a documented security consideration for webhook configuration, not a hidden malicious instruction. No evidence of credential harvesting, data exfiltration, or obfuscation was found in the provided definition.
Audited Apr 18, 2026 · audit v1.0
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...