The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of React applications that ingest and render data from external API endpoints (e.g., https://api.example.com or /api/). This creates a data ingestion surface that could be exploited if malicious content is served by the connected API.
Ingestion points: Data fetching implementations in myDataProvider and the dataProvider configuration in App.tsx (found in SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded content are included in the code templates.
Capability inventory: The skill allows for file system writes (project scaffolding) and shell command execution via project management tools.
Sanitization: The provided examples lack explicit sanitization or validation logic for data retrieved from external providers before it is rendered in the UI.
[EXTERNAL_DOWNLOADS]: The skill provides instructions to download the Refine project initialization tool and framework dependencies using npm create refine-app@latest and npm install. These involve fetching code from the public npm registry.
[COMMAND_EXECUTION]: The skill includes instructions to execute shell commands for project setup, dependency installation, and running the development server (npm create, npm install, npm run dev).

refine