telegram-bot-builder
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Potential for Indirect Prompt Injection.
- Ingestion points: The bot templates ingest untrusted user input via
ctx.message.text(inSKILL.md). - Boundary markers: No specific delimiters or instructions are provided to the model to ignore instructions embedded in user messages.
- Capability inventory: The provided code demonstrates the ability to send messages (
ctx.reply), handle payments (ctx.replyWithInvoice), and modify state (activatePremium). - Sanitization: The code snippets do not include input sanitization or validation, which is expected for basic educational templates but presents a surface for injection attacks against the resulting bot's logic.
- [DATA_EXFILTRATION] (SAFE): The skill correctly demonstrates the use of
process.env.BOT_TOKENandprocess.env.PAYMENT_TOKEN, encouraging the use of environment variables rather than hardcoding sensitive credentials. - [REMOTE_CODE_EXECUTION] (SAFE): No patterns for remote script execution, dynamic code evaluation (eval/exec), or unauthorized subprocess spawning were detected.
Audit Metadata