The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run shell commands to initialize and verify the project environment, specifically using npx @subframe/cli@latest init and npm run dev.
[REMOTE_CODE_EXECUTION]: The skill utilizes npx to download and execute the latest version of the @subframe/cli package from the npm registry. This is a legitimate vendor resource provided by the skill's author (subframeapp).
[EXTERNAL_DOWNLOADS]: The skill references external configuration resources, including fetching font assets from Google Fonts (fonts.googleapis.com, fonts.gstatic.com) and directing users to the official Subframe authentication page (app.subframe.com).
[INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it ingests project metadata and user-provided configuration strings which are subsequently interpolated into shell command arguments.
Ingestion points: User-provided installation prompts (containing project IDs/tokens), list_projects tool output, and get_theme tool output.
Boundary markers: None explicitly defined in the instructions for these data inputs.
Capability inventory: Execution of shell commands through npx and directory/file structure modifications via the CLI.
Sanitization: The skill does not specify explicit sanitization, relying on the CLI tool's argument parsing logic.

install