telegram

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements patterns for processing untrusted user data from Telegram messages, creating a vulnerability surface for indirect prompt injection when this data is passed to AI models or used in moderation logic.\n
  • Ingestion points: Untrusted data is ingested via the update.message.text field, as demonstrated in the AI automation example in SKILL.md and the moderation logic example in references/chat-management.md.\n
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands were found in the provided code snippets.\n
  • Capability inventory: The skill possesses capabilities to interact with the Telegram Bot API, including sending messages and managing chat members, as implemented in assets/boilerplate/nodejs/src/bot-client.ts and assets/boilerplate/python/bot.py.\n
  • Sanitization: Sanitization is limited to basic keyword filtering in the moderation example and is entirely absent in the AI integration snippet.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 05:50 PM