telegram-bot-builder

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for processing untrusted user input from the Telegram API, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: User input is ingested via bot.on('text') and bot.command() handlers in SKILL.md.
  • Boundary markers: The provided code snippets do not include explicit delimiters or instructions for the agent to ignore embedded commands in user messages.
  • Capability inventory: The skill describes architecture for AI-powered bots and business logic services, which may include file operations or network requests in a full implementation.
  • Sanitization: The snippets lack input validation or sanitization for the received text before it is processed or echoed back to the user.
  • [SAFE]: The skill demonstrates security best practices by referencing environment variables (process.env.BOT_TOKEN, process.env.PAYMENT_TOKEN) rather than hardcoding sensitive API credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:19 AM
Security Audit — agent-trust-hub — telegram-bot-builder