ai-coding-spend
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The workflow.md file provides instructions to download the Bruin CLI installer from the official website (getbruin.com) and clone a resource repository from the author's GitHub (bruin-data). These sources are authoritative for the tools described in the skill.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute Bruin CLI commands (bruin version, bruin upgrade, bruin init, bruin run, bruin query) to manage the data pipeline. This is the primary intended function of the skill and is carried out with explicit user approval as per the instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes usage data from AI platforms (Cursor and Claude Code), which serves as an external, potentially untrusted input source.
- Ingestion points: Usage data CSVs and database marts (SKILL.md, analysis.md).
- Boundary markers: The instructions tell the agent to state definitions and windows clearly but do not specify technical delimiters for the data content itself.
- Capability inventory: The skill uses the Bruin CLI for SQL queries and orchestration.
- Sanitization: No explicit validation of individual data strings is mentioned before interpretation by the agent.
Audit Metadata