tawkto
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the user to install the @membranehq/cli package from the NPM registry. This is a vendor-owned tool necessary for interacting with the Membrane ecosystem.
- [COMMAND_EXECUTION]: The skill instructions include the use of shell commands to manage connections and execute API actions via the Membrane CLI.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for Tawk.to data (chats, tickets) which enters the agent context via CLI outputs. Since this data originates from external users, it could contain instructions aimed at the agent. No boundary markers or sanitization logic are defined in the skill instructions to mitigate this.
Audit Metadata