marketing-analytics
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides instructions to install or upgrade the Bruin CLI tool by downloading and pipe-executing a shell script from the vendor's official website (
https://getbruin.com/install/cli). - [COMMAND_EXECUTION]: The skill performs extensive local command execution using the
bruinCLI andgit. It includes operations for project initialization, connection testing, and running data pipelines. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external sources such as ad platforms (Google Ads, Meta, LinkedIn) and CRM systems (HubSpot, Salesforce). This processing of untrusted external data represents a potential attack surface.
- Ingestion points: Ad platform spend reports, raw database tables, and external documentation files referenced during setup.
- Boundary markers: None explicitly defined in the instructions for data interpolation.
- Capability inventory: The skill utilizes the
bruinCLI to execute data transformations and can read/write local project configuration files. - Sanitization: The instructions do not specify any explicit sanitization or escaping methods for external data before processing.
Audit Metadata