support-analytics
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the Bruin CLI installation script from the official vendor domain at https://getbruin.com/install/cli.
- [REMOTE_CODE_EXECUTION]: Executes the downloaded installation script directly in the shell using curl and sh. This is documented as the standard setup procedure for the vendor's tooling.
- [COMMAND_EXECUTION]: Operates various command-line utilities including the bruin CLI for pipeline management, git for repository operations, and the claude mcp command for server configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and interpret external content from templates, pipeline variables, and README files, which introduces a potential vector for malicious instructions to influence agent behavior.
- Ingestion points: Reads pipeline.yml variables, asset filters, and user-provided model definitions as described in workflow.md and analysis.md.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The skill retains the ability to execute CLI commands and run data pipelines based on the processed configuration.
- Sanitization: There are no explicit steps for sanitizing or validating external inputs before they are incorporated into the agent's context.
Audit Metadata