sergei-mikhailov-tg-channel-reader

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection surface. The skill fetches content (posts and comments) from external Telegram channels which are attacker-controllable sources.
  • Ingestion points: Raw message and comment text are retrieved in reader.py and reader_telethon.py.
  • Boundary markers: The data is returned to the agent in a structured JSON format, providing clear separation between data and control.
  • Capability inventory: The agent is intended to summarize and analyze this text, which could lead to following embedded instructions if not handled by agent-level guardrails.
  • Sanitization: Content is passed as raw strings within the JSON output without specific character escaping.
  • [EXTERNAL_DOWNLOADS]: The skill depends on established and well-known Python libraries (pyrogram, telethon, and tgcrypto) for its core functionality. These are standard tools in the Telegram development ecosystem and are fetched from official package registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:15 PM