telegram-automation

Warn

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external Model Context Protocol (MCP) server located at 'https://rube.app/mcp'. This server acts as the intermediary for all Telegram operations and is not associated with a known trusted vendor or the skill author.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection due to the nature of Telegram automation.
  • Ingestion points: The skill retrieves untrusted data from external sources via tools like TELEGRAM_GET_UPDATES and TELEGRAM_GET_CHAT_HISTORY (file: SKILL.md).
  • Boundary markers: There are no instructions provided to the agent to use delimiters or ignore potential commands embedded within the retrieved Telegram messages.
  • Capability inventory: The skill possesses significant capabilities, including sending messages, uploading documents, and managing chat administrative settings across multiple TELEGRAM_* tools (file: SKILL.md).
  • Sanitization: There is no evidence of sanitization or validation for content received from the Telegram API before it is added to the agent's context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 06:26 PM