chatbot-builder

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The instructions guide the user to install the @membranehq/cli package from the NPM registry. This is the official CLI for the platform and is a trusted vendor resource.
  • [COMMAND_EXECUTION]: The skill uses membrane CLI commands to manage connections and trigger API actions. While user-provided input is used in some commands (like action intents), this is consistent with the skill's purpose as a developer integration tool.
  • [PROMPT_INJECTION]: The skill interacts with external data from the Chatbot Builder API, creating a surface for indirect prompt injection. \n
  • Ingestion points: Data enters the agent's context through output from membrane action run and membrane request calls. \n
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded commands in retrieved data. \n
  • Capability inventory: The skill can perform state-changing actions such as sending messages and creating contacts. \n
  • Sanitization: No specific data sanitization or validation processes are described for the API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 12:15 PM