The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to run npx @open-slide/cli init, which downloads and executes a CLI tool from the npm registry. This pattern allows for the execution of arbitrary code defined in the external package on the host machine.- [COMMAND_EXECUTION]: The workflow requires the execution of multiple shell commands including pnpm install, pnpm dev, pnpm build, and pnpm sync:skills to manage the local development and build environment.- [EXTERNAL_DOWNLOADS]: The skill downloads and updates dependencies from the npm registry (@open-slide/cli, @open-slide/core) and references an external GitHub repository for the framework source code.- [DATA_EXFILTRATION]: The skill provides procedures for deploying the compiled static site (dist/ folder) to external hosting providers such as Vercel, Netlify, Cloudflare Pages, and Zeabur.- [PROMPT_INJECTION]: The skill processes untrusted input and files, creating a surface for indirect prompt injection.
Ingestion points: The skill ingests user-provided topic and style_direction inputs, and reads content from DESIGN.md and workspace theme files.
Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore potentially malicious instructions embedded in the processed data.
Capability inventory: The skill possesses shell execution capabilities (npx, pnpm) and can trigger network operations via deployment scripts.
Sanitization: The skill does not describe any sanitization, filtering, or validation steps for the external content it processes.

open-slide-studio