The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform shell operations to manage the documentation project, including project scaffolding, dependency management, and file inspection.
Execution of npx nuxi init for project initialization in SKILL.md.
Usage of pnpm dev and pnpm build for development and production tasks in SKILL.md.
File inspection using cat package.json and ls content/ in SKILL.md.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download of project templates from external sources.
Fetches templates from the author's GitHub repository: gh:mhaibaraai/movk-nuxt-docs/templates/default and gh:mhaibaraai/movk-nuxt-docs/templates/module.
[REMOTE_CODE_EXECUTION]: The initialization step with npx nuxi init downloads and executes a remote template. This represents a remote code execution surface, although it targets the vendor's own infrastructure as part of a standard framework setup.
[PROMPT_INJECTION]: An indirect prompt injection surface exists because the skill processes documentation content provided in Markdown files.
Ingestion points: Files in the content/ directory, such as content/docs/*.md and content/index.md.
Boundary markers: Absent; there are no specific delimiters or instructions for the agent to ignore potentially malicious directions embedded within the documentation content.
Capability inventory: The skill has the capability to execute shell commands and read/write files as part of its documented workflow.
Sanitization: Absent; the instructions do not specify any sanitization or validation of documentation content before it is processed.
[DATA_EXFILTRATION]: The configuration guide in references/configuration.md advises users to store sensitive API keys (NUXT_GITHUB_TOKEN, AI_GATEWAY_API_KEY, OPENROUTER_API_KEY) in a .env file. This creates a data exposure surface if the agent is later prompted to read or manage environmental configurations.

create-docs