skills/sqrdao/sqrskills/telegram-send/Gen Agent Trust Hub

telegram-send

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python scripts to perform its core functions.
  • Executes list_groups.py to identify available Telegram chats from local session data.
  • Executes send.py to transmit messages to specified Telegram chat IDs.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with external APIs to fulfill its functionality.
  • Connects to the official Telegram Bot API (api.telegram.org) to resolve chat names and send messages.
  • Optionally connects to a YouAI backend API (YOUAI_API_URL) for fallback group discovery.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external and local sources that could potentially be influenced by untrusted parties.
  • Ingestion points: Reads session files from ~/.nanobot/workspace/sessions/ and OpenClaw session paths, and fetches chat metadata (group names) from the Telegram API.
  • Boundary markers: The instructions do not define explicit boundary markers or directives to ignore instructions embedded within the group names or session data being processed.
  • Capability inventory: The skill possesses file-read access to local session/config files and network access to the Telegram API.
  • Sanitization: The send.py script utilizes html_escape to sanitize the message payload before sending it to the Telegram API, mitigating basic HTML injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:25 PM