interactive-bot
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to verify the environment and run a local TypeScript bot script (
bot.ts) using thebunruntime. - [PROMPT_INJECTION]: The skill exhibits a surface for Indirect Prompt Injection (Category 8) by processing untrusted data from a user's Gmail inbox through an AI model.
- Ingestion points: Retrieves email content from the user's Gmail inbox via
/inbox,/search, and/readcommands. - Boundary markers: The provided documentation does not specify the use of delimiters or 'ignore' instructions to prevent the model from following commands embedded within emails.
- Capability inventory: The skill has access to
Bash,Read,Grep, andGlobtools, and executes a script that communicates with external Telegram and Gmail APIs. - Sanitization: There is no evidence of sanitization or filtering of email content before it is processed by the AI routing system.
Audit Metadata