The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads project-specific files (e.g., README.md, package.json, and source code) to extract context for generating documentation. This creates a surface for indirect prompt injection where malicious content in those files could influence the agent's behavior or lead to the generation of malicious documentation sites.\n
Ingestion points: README.md, package.json, and files within src/ or lib/ directories (SKILL.md).\n
Boundary markers: The skill does not define specific delimiters or instructions to ignore instructions embedded within the ingested data.\n
Capability inventory: The skill performs file reading and writing operations, and provides commands for the user to execute package installation and development servers.\n
Sanitization: No explicit sanitization or validation of the ingested external content is mentioned.\n- [COMMAND_EXECUTION]: The skill provides instructions for the user to execute shell commands such as npm install and npm run dev to initialize and run the generated documentation site.\n- [EXTERNAL_DOWNLOADS]: Fetches documentation templates and component definitions from the official Nuxt UI website (ui.nuxt.com).

create-docs