rex
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
membraneCLI tool to interact with the Rex API. These commands are part of the intended integration logic and use the vendor's official toolset. - [EXTERNAL_DOWNLOADS]: The instructions include installing the
@membranehq/clipackage from the npm registry. This is an official tool provided by the vendor (membranedev) for the purpose of the integration. - [DATA_EXFILTRATION]: The skill transmits data to
getrex.ioandgetmembrane.com. These are the legitimate service and platform domains associated with the skill's functionality. No unauthorized data exfiltration patterns were detected. - [PROMPT_INJECTION]: The skill ingests data from the external Rex API via
membrane action runormembrane request, creating a surface for potential indirect prompt injection. However, the skill uses a controlled integration environment and does not exhibit direct injection vulnerabilities.
Audit Metadata