The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill implements a documentation retrieval workflow that ingests data from external URLs, creating a surface for potential indirect prompt injection.
Ingestion points: The skill fetches external content from multiple locations including https://render.com/docs/mcp-server.md, https://render.com/docs/cli.md, and https://render.com/docs/cli-reference.md.
Boundary markers: The instructions lack explicit boundary delimiters or "ignore embedded instructions" warnings for the fetched external content.
Capability inventory: The skill utilizes curl for network requests and can execute commands via the render CLI and claude CLI tools, as well as modify local configuration files like ~/.cursor/mcp.json.
Sanitization: No sanitization or filtering logic is specified for the documentation content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill retrieves documentation and configuration guidelines from official Render domains.
Evidence: Fetches Markdown and HTML resources from render.com to provide up-to-date platform information.
[COMMAND_EXECUTION]: The skill provides instructions to configure AI tools using system commands and configuration files.
Evidence: Includes instructions for executing claude mcp add to configure the server and render whoami to verify identity. It also provides a template for modifying the ~/.cursor/mcp.json configuration file.

render-mcp