Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
AgentCloak sits between an AI agent and your email account, providing search, read, and draft access through a 4-stage security pipeline (blocklist, HTML sanitization, PII redaction, prompt injection detection). Credentials stay server-side; the agent only sees filtered content. Available as a hosted service or self-hosted instance.
Unlike raw email skills that give agents unfiltered inbox access, AgentCloak runs credentials and content through a server-side security pipeline so the agent never sees passwords, PII, or prompt injection attempts.
When to use it
- Finding unread emails without exposing email credentials to the agent
- Drafting reply emails for human review before sending
- Reading full conversation threads for context while filtering PII
- Blocking financial and security-sensitive emails from agent access
- Checking label-based unread counts across the inbox
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Find my unread emails from this week and draft a reply to the most recent one from my manager
- 1Calls search_emails with query 'is:unread newer_than:7d' to retrieve recent unread messages
- 2Calls read_email on the most recent result to get filtered, PII-redacted content
- 3Identifies the thread and sender from the sanitized email body
- 4Calls create_draft with a composed reply and in_reply_to_thread_id set to the original thread
Draft reply created in the email account, ready for user review before sending
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.