open-exchange-rates
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
membraneCLI to manage connections, search for actions, and execute API calls. This is the intended behavior for integrating with the Membrane platform. - [EXTERNAL_DOWNLOADS]: Includes instructions to install the
@membranehq/clipackage from the official NPM registry. This package belongs to the vendor's toolchain and is necessary for the skill's functionality. - [CREDENTIALS_UNSAFE]: The skill documentation explicitly warns against asking for user API keys or tokens. It leverages a managed authentication flow (
membrane connect), which is a secure alternative to hardcoding or manually handling credentials. - [SAFE]: Analysis of the skill instructions and metadata revealed no evidence of prompt injection, obfuscation, persistence mechanisms, or unauthorized data exfiltration.
Audit Metadata