skills/qwibitai/nanoclaw/add-telegram/Gen Agent Trust Hub

add-telegram

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses git fetch and git show to pull code from the 'channels' branch of the existing repository. It also installs the @chat-adapter/telegram package from the NPM registry. These downloads are intended for feature delivery and originate from expected project sources.
  • [COMMAND_EXECUTION]: Installation involves standard shell commands including git operations, file redirection, and pnpm for package management and building. These commands are necessary and appropriate for adding the Telegram channel functionality.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is created as the agent will ingest untrusted messages from the Telegram platform.
  • Ingestion points: Incoming messages from Telegram chats and groups (as described in the Channel Info section).
  • Boundary markers: No specific boundary delimiters or 'ignore' instructions are provided in the skill body for handling incoming message data.
  • Capability inventory: The agent has permissions to perform project builds and file system modifications as part of its development role.
  • Sanitization: The skill includes a dedicated helper file (telegram-markdown-sanitize.ts) for managing content formatting and safety.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 08:58 PM