The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the bruin CLI to perform diagnostic operations, including bruin cloud runs diagnose, bruin cloud instances failed-logs, and bruin query. These commands are standard administrative tools for the Bruin platform.
[INDIRECT_PROMPT_INJECTION]: The skill involves analyzing external content such as pipeline logs, SQL/Python source code from the repository, and database row samples during investigation. 1. Ingestion points: Data enters the agent's context through CLI outputs and repository file reads as defined in the SKILL.md investigation steps. 2. Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data being analyzed. 3. Capability inventory: The skill has the ability to execute shell commands via the Bruin CLI and interact with the Bruin Cloud API. 4. Sanitization: There are no explicit steps for sanitizing or filtering the output of diagnostic commands before analysis.

duplicate-investigate