The Agent Skills Directory

[Data Exposure] (LOW): The skill handles sensitive information including Telegram API IDs, hashes, and session strings. It instructs users to store these in a .env file, which is a common but sensitive storage practice for credentials.
[Command Execution] (LOW): The documentation lists commands for executing local Python scripts (generate_session.py and telegram_init.py). These are standard initialization routines for the described functionality.
[Indirect Prompt Injection] (LOW): The skill ingests data from the Telegram API, such as group names and channel titles. As untrusted external data, this represents a potential surface for indirect injection if displayed or processed by the agent without proper boundary markers, though no active exploitation is present.

telegram-init