telegram-bot
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection where untrusted user input is processed.
- Ingestion points: User-generated Telegram messages (text, voice transcripts, and document content) enter the context via triggers and handlers defined in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the system prompts or workflow configurations.
- Capability inventory: The skill includes tools like
telegram_send_messageandtelegram_send_photothat can be influenced by the AI's output. - Sanitization: There is no evidence of input validation or sanitization before external content is interpolated into AI prompts in the provided instructions.
- [SAFE]: The skill utilizes the official Telegram API domain (api.telegram.org) for legitimate bot configuration and communication tasks.
Audit Metadata