Telegram Bot API

PassAudited by VirusTotal on May 11, 2026.

Overview

Type: OpenClaw Skill Name: telegram-bot-api Version: 1.0.0 The skill is designed to assist with Telegram Bot API interactions, which inherently involves handling sensitive data like bot tokens and making network requests. The skill explicitly states that all external communication is directed solely to `https://api.telegram.org` and no other endpoints, as detailed in `SKILL.md`. Furthermore, `setup.md` provides clear instructions for the AI agent to ask for user permission before saving bot tokens locally to `~/telegram-bot-api/bots/{botname}.md` and to avoid displaying them. The use of `curl` and other command-line tools (like `ffmpeg`, `openssl`, `ngrok`, `cloudflared`) is for legitimate, transparent purposes related to bot development and webhook setup. There is no evidence of malicious intent, unauthorized data exfiltration, or deceptive prompt injection.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Anyone with the saved bot token could send messages or manage the bot within its permissions.

Why it was flagged

A Telegram bot token is a credential that can control the bot; saving it locally is disclosed and permission-based, but users should treat it as sensitive.

Skill content
If they share a token: 1. Ask permission: "Want me to save this token locally so I can help you test?" 2. If yes, save to `~/telegram-bot-api/bots/{botname}.md`
Recommendation

Save tokens only for bots you intend the agent to help manage, keep the local files private, and revoke/regenerate the token if it is exposed.

What this means

If used with a privileged bot token, commands can affect real chats, messages, and members.

Why it was flagged

The API reference includes high-impact bot actions such as moderation and deletion; these are expected for a Telegram Bot API skill but should remain user-directed.

Skill content
### banChatMember
curl -X POST "https://api.telegram.org/bot${TOKEN}/banChatMember" ...
### deleteMessage
curl -X POST "https://api.telegram.org/bot${TOKEN}/deleteMessage"
Recommendation

Use test chats first and require explicit confirmation before sending public messages, deleting content, banning users, or changing webhook state.

What this means

Stored bot configuration may persist beyond the current conversation and could be reused later by the agent or exposed if local files are readable.

Why it was flagged

The skill defines persistent local memory that can include bot tokens and defaults reused across future tasks.

Skill content
Create `~/telegram-bot-api/bots/{botname}.md`:
...
token: {BOT_TOKEN}
Recommendation

Review the memory files periodically, remove stale tokens, and restrict file access on shared machines.

What this means

The token could appear in webhook configuration, server logs, or shared URLs if this pattern is used.

Why it was flagged

One webhook example places the bot token in the webhook URL path; this can undermine the token-protection guidance if that URL is copied or logged.

Skill content
-d "url=https://example.com/webhook/${TOKEN}"
Recommendation

Prefer the later `secret_token` webhook pattern and avoid embedding the bot token itself in public or logged URLs.