finance-accounting

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The workflow.md file contains a command to download and execute the Bruin CLI installation script: curl -LsSf https://getbruin.com/install/cli | sh. This resource originates from the official vendor domain and is a standard procedure for this tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external financial data from QuickBooks Online, which serves as a potential surface for indirect prompt injection.
  • Ingestion points: Data enters the context through Bruin pipelines and QuickBooks templates (SKILL.md).
  • Boundary markers: The skill instructs the agent to state the environment basis and company context, but does not implement formal technical delimiters for ingested data.
  • Capability inventory: The skill enables the use of Bruin CLI tools for pipeline management and execution, as well as local git and environment configuration.
  • Sanitization: No specific sanitization or filtering logic for the ingested records is defined in the instructions.
  • [COMMAND_EXECUTION]: The skill directs the agent to execute various Bruin CLI commands (bruin init, bruin run, bruin validate) to manage the data lifecycle. These operations are performed with user approval and are consistent with the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 04:40 PM