telegram-automation
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to connect to a third-party MCP server at
https://rube.app/mcpas part of its setup process. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by processing data from external Telegram chats.
- Ingestion points: Untrusted content enters the agent's context through the
TELEGRAM_GET_UPDATESandTELEGRAM_GET_CHAT_HISTORYtools. - Boundary markers: The instructions do not define delimiters or system prompts to help the agent distinguish between its instructions and the content of the Telegram messages.
- Capability inventory: The skill provides tools with significant capabilities, including message transmission (
TELEGRAM_SEND_MESSAGE), file sharing (TELEGRAM_SEND_DOCUMENT), and chat management (TELEGRAM_DELETE_MESSAGE,TELEGRAM_EXPORT_CHAT_INVITE_LINK). - Sanitization: The skill lacks guidance on sanitizing or filtering input from chat histories or updates, leaving the agent vulnerable to instructions embedded within those messages.
Audit Metadata