telegram-bot-builder
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documents the creation of bot handlers that process untrusted user input, establishing a potential attack surface for indirect prompt injection via the Telegram API.\n
- Ingestion points: The skill utilizes
bot.on('text')andbot.handleUpdate(req.body)to ingest external messages as shown inSKILL.md.\n - Boundary markers: The basic code templates do not implement specific delimiters or instructions to the model to ignore embedded commands within the user-provided message text.\n
- Capability inventory: The templates have access to the Telegram Bot API capabilities, including sending messages (
ctx.reply) and processing payments (ctx.replyWithInvoice).\n - Sanitization: The instructional snippets do not include complex input sanitization or validation of the user's text before processing or echoing it.\n- [SAFE]: No malicious behavior, obfuscation, or unauthorized data exfiltration patterns were identified. The skill follows industry standards for secure bot development, such as using environment variables for tokens and suggesting production-grade error handling.
Audit Metadata