The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill scaffolds projects by interpolating user-provided information into file templates, creating a surface for indirect injection if malicious metadata is provided.
Ingestion points: The "Gather Project Info" table in SKILL.md collects fields like Project Name and npm scope which are used as template variables.
Boundary markers: No specific delimiters or warnings for embedded instructions are specified for the interpolated fields in the generated files.
Capability inventory: The skill uses pnpm, cargo, and npx (in SKILL.md and templates/AGENTS.md) to install dependencies and verify the project.
Sanitization: The instructions do not define sanitization or validation steps for the user-supplied strings before they are written to the filesystem.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of additional AI agent skills and dependencies from remote repositories during the setup process.
Evidence: SKILL.md includes commands to download and install rust-node-ci and rust-npm-publish from the onsager-ai/dev-skills repository.
Evidence: templates/AGENTS.md provides instructions to install skills from the codervisor organization's repositories.
[COMMAND_EXECUTION]: The skill performs shell-based operations to initialize and verify the scaffolded environment.
Evidence: SKILL.md triggers pnpm install, pnpm build, and cargo check --workspace to ensure the new project structure is valid and functional.

rust-node-bootstrap