telegram

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill directly fetches and formats user-generated Telegram content from the open web (e.g., scripts/telegram_fetch.py functions like fetch_recent, search_messages, fetch_thread_messages and download_media) and outputs it as Markdown/JSON for the agent to read (format_output / default Markdown to stdout), so untrusted third-party messages could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 09:32 AM