add-telegram

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses npm install to download and install the node-telegram-bot-api package and its types. This is a well-known and standard library for interacting with the Telegram Bot API.
  • [DATA_EXPOSURE]: The skill manages a sensitive TELEGRAM_BOT_TOKEN. It explicitly instructs the agent to store this token in an encrypted vault and cautions against writing it to .env files or logs, which is a security best practice.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes a communication channel that ingests data from an untrusted external source (Telegram messages).
  • Ingestion points: The TelegramChannel class in src/channels/telegram.ts processes incoming message content via the bot.on('message') listener.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided in the implementation snippet.
  • Capability inventory: The skill's environment is configured with access to tools including write_file, read_file, run_code, and install_pkg.
  • Sanitization: Incoming message text is passed to the internal handler without prior sanitization, representing a standard attack surface for chat-based agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 05:14 AM
Security Audit — agent-trust-hub — add-telegram