telegram-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from external Telegram chats.
  • Ingestion points: The skill utilizes TELEGRAM_GET_UPDATES and TELEGRAM_GET_CHAT_HISTORY to retrieve message content from external users (documented in SKILL.md).
  • Boundary markers: The instructions do not define boundary markers or clear-text delimiters to separate untrusted chat data from agent instructions.
  • Capability inventory: The agent has permissions to perform significant actions based on processed data, including TELEGRAM_SEND_MESSAGE, TELEGRAM_DELETE_MESSAGE, TELEGRAM_FORWARD_MESSAGE, and TELEGRAM_SET_MY_COMMANDS (all found in SKILL.md).
  • Sanitization: There is no evidence of message sanitization, filtering, or validation before the content is interpolated into the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:24 PM
Security Audit — agent-trust-hub — telegram-automation