The Agent Skills Directory

[SAFE]: The skill retrieves business metrics from vendor-managed infrastructure using standard tool calls.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data which represents a theoretical injection surface.
Ingestion points: Business data is ingested through tools like list_orders and get_message_analytics in SKILL.md.
Boundary markers: No explicit boundaries or instructions are provided to the model to ignore content within the data.
Capability inventory: Capabilities are limited to data retrieval and dashboard rendering (render_analytics_dashboard) without shell or file-write access.
Sanitization: No explicit sanitization or filtering of the ingested data is described in the instructions.

inttegro-daily-brief