The Agent Skills Directory

[PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection due to its core functionality of processing external data formats. • Ingestion points: The skill uses d3.csv() and d3.json() to load external data in resources/getting-started.md and resources/workflows.md. • Boundary markers: No explicit delimiters or instructions to the agent to ignore embedded instructions in the data are provided in the templates. • Capability inventory: The skill documents the use of .html() for DOM manipulation in resources/selections-datajoins.md and provides patterns for interactive event handlers, which can be vulnerable if untrusted data is rendered. • Sanitization: No explicit sanitization or validation of ingested data content is present in the code examples.
[EXTERNAL_DOWNLOADS]: The skill correctly references external JavaScript libraries from well-known and established content delivery networks. • Evidence: Fetches the D3 library from https://cdn.skypack.dev/d3@7 and https://d3js.org/d3.v7.min.js as documented in resources/getting-started.md.

d3-visualization