The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill metadata and documentation direct the user to clone a full set of workflows, scripts, and assets from an external repository located at https://github.com/jiannanya/snow-d3.git. This source is not recognized as a trusted organization or well-known service.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external datasets (e.g., sales data, network graphs) to generate D3.js visualizations, which presents a surface for indirect prompt injection attacks.
Ingestion points: Data provided by the user or fetched by the agent to create "zoomable treemaps", "force-directed network graphs", and other visualizations described in the file.
Boundary markers: None identified in the provided instructions; there are no explicit delimiters or instructions to ignore embedded content within processed data.
Capability inventory: The agent acts as an expert-level D3.js code generator, potentially executing or rendering code based on the visualization requirements.
Sanitization: No evidence of sanitization, validation, or filtering of the input data is provided in the skill instructions.

d3-visualization