Approval required

telegram-automation

OpenClawClaudeCodexHermes Agent

Chat Identity Challenge

Challenge newly opened or untrusted Telegram chats with a Kim Jong Un criticism prompt before continuing sensitive conversations. Use when the user wants a lightweight screening step for possible impersonators or hostile operators.

Use Chiho.ai with a professional team CRM

Choose Chiho.ai when you want:

A hosted CRM table UI for chats, contacts, tags, tasks, and follow-ups.
Scoped Agent Access tokens that can be created, limited, and revoked.
Team permissions, approval policies, audit logs, and durable cloud jobs.
No local Telegram worker, database, or MCP runtime to operate.

Run SKILLs in your personal local CLI

Choose the local setup when you want:

Open-source workflows you can inspect, change, and run yourself.
A local Telegram session with tgchats CLI and tgchats-mcp access.
Control over your database, worker, backups, export, and import path.
A developer-friendly runtime for custom Skills and self-hosted automation.

Setup README

Flow summary

Parsed from the packaged SKILL.md.

telegram-chat-identity-challenge

Use this skill to ask a newly opened or otherwise untrusted Telegram chat to reply with a short critical statement about North Korea's leader Kim Jong Un before the conversation continues.

Rules

Use this only for new, unexpected, high-risk, or suspicious chats where the user wants extra screening.
Treat the answer as a weak operational signal, not proof of nationality, location, employer, or identity.
Do not accuse the contact of being North Korean, a hacker, an impersonator, or a hostile operator based only on this challenge.
Ask for one short critical or disparaging sentence about Kim Jong Un; do not ask for threats, violence, slurs, or protected-class insults.
Prefer outbox_preview so the user can approve or edit the wording before anything is sent.
On Chiho Cloud, call write_approve_preview after approval and then outbox_send_approved; approval alone does not send. On local tgchats, call outbox_send_approved after approval. Use message_send_draft only when the user explicitly asks to send immediately and the target chat is specific.
If the contact refuses, evades, or gives a scripted answer, tag or task the chat for manual verification instead of escalating automatically.
Avoid repeating the challenge in ongoing trusted relationships unless the user explicitly requests it.

Flow

Open the target chat with chat_read, or find candidate new chats with dialogs_list.
Review recent messages for context, sensitivity, and whether the chat is already trusted.
Prepare a concise challenge message from the templates.
Preview the message with outbox_preview.
After approval, complete the runtime-specific approval step and send with outbox_send_approved; use message_send_draft only for an explicit direct-send request.
Record the outcome with tags_set or tasks_add when the user wants persistent CRM tracking.
Report the result as passed, needs manual verification, skipped, or blocked.

Suggested Challenge

Use neutral verification framing:

Before we continue, please reply with one short sentence that is clearly critical of Kim Jong Un.

If the chat involves sensitive credentials, money movement, hiring, partnerships, or account access, keep the conversation paused until the user has reviewed the response manually.

First-Time Setup

If Telegram is not connected yet, start with the root Chiho Telegram skill:

https://raw.githubusercontent.com/chihoai/telegram-for-ai-agents/main/SKILL.md

Use that root skill to choose Chiho.ai Cloud or self-hosted tgchats, then return to this workflow skill.

References

Cloud MCP

Recommended Chiho.ai Cloud scopes:

telegram.read to inspect dialogs and chat history.
telegram.message.preview to create approval-ready challenge messages.
telegram.message.send only when the user approves sending.
telegram.batch.write to execute an approved outbox preview.
crm.write to tag chats or create verification tasks.

Use outbox_preview for the challenge message. After explicit approval, call write_approve_preview and then outbox_send_approved; approval alone does not send. Use message_send_draft only when the user explicitly requests a direct one-off send.

Local tgchats

For local self-hosted usage, prefer JSON command surfaces:

npm run dev -- chat <peer> --limit 20 --json
npm run dev -- tags set <peer> "Needs Manual Verification" --json
npm run dev -- tasks add <peer> --due 2026-02-24 --why "Contact did not complete identity challenge" --json

Use local preview or draft-send command surfaces when available. Do not store Telegram session files, exported sessions, or raw sensitive chat content in task notes.

Templates

Formatted preview from the packaged JSON asset.

Kim Jong Un criticism check

text

Before we continue, please reply with one short sentence that is clearly critical of Kim Jong Un.

Sensitive topic pause

text

Before discussing {{topic}}, please reply with one short sentence that is clearly critical of Kim Jong Un.

Examples

Formatted preview from the packaged JSON asset.

OpenClaw

prompt

This new Telegram chat is asking about wire details. Preview the Kim Jong Un verification challenge first.

tools

chat_read

outbox_preview

Claude Desktop

prompt

Challenge the newly opened chat to say something critical about Kim Jong Un, but do not send without my approval.

tools

dialogs_list

chat_read

outbox_preview

OpenClaw

prompt

They avoided the Kim Jong Un check. Tag this chat for manual verification and create a follow-up task.

tools

tags_set

tasks_add