botpenguin

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli global package via npm, which is the official tool for the vendor infrastructure mentioned in the metadata.
  • [COMMAND_EXECUTION]: It uses the membrane command-line tool for authentication, connection management, and executing API actions like listing chats and sending messages.
  • [SAFE]: The skill is a standard platform integration. While it ingests external chat data from BotPenguin (creating a theoretical surface for indirect prompt injection), this is central to its documented purpose and no suspicious behavior was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 11:23 PM