The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and does not contain any executable scripts or binary files.
[EXTERNAL_DOWNLOADS]: The documentation references downloading tools and templates from official, well-known sources such as pnpm.io and GitHub repositories associated with Vercel. These are standard development practices and do not represent a security risk.
[COMMAND_EXECUTION]: Provides detailed instructions for using the Turborepo CLI, including commands for task execution, workspace generation, and monorepo pruning. All documented commands are standard build tool operations.
[REMOTE_CODE_EXECUTION]: Documentation for GitLab CI includes an example command curl -f https://get.pnpm.io/v6.16.js | node to install pnpm. This targets a well-known service and is a common installation pattern for CI environments.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to read and act upon configuration files like turbo.json. While these files could contain malicious prompts in untrusted repositories, the capability is fundamental to the skill's purpose as a monorepo management tool.
Ingestion points: Reads turbo.json, package.json, and pnpm-workspace.yaml from the workspace.
Boundary markers: None present in the reference documentation.
Capability inventory: Includes turbo run, turbo gen, and turbo query for task execution and workspace modification.
Sanitization: None described for parsing project configuration data.

turborepo