The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The scripts/install.sh script clones the kimlawtech/korean-privacy-terms repository from GitHub to the user's home directory skill folders.
[REMOTE_CODE_EXECUTION]: The skill instructions direct the agent to run logic, interview protocols, and rendering scripts (interview.md, render.md, install.md) contained within the downloaded external repository. It also utilizes npx to execute the @nomadamas/k-skill package from the npm registry.
[INDIRECT_PROMPT_INJECTION]: The skill conducts an interview with the user and interpolates the responses into generated source code and legal documents, which presents a surface for instruction injection via user data.
Ingestion points: User responses provided during the mandatory 10-step interview process described in instruction.md.
Boundary markers: None identified in the wrapper instructions to prevent the agent from following instructions embedded in user input.
Capability inventory: The skill writes files to the local project (src/app/privacy/page.tsx, src/app/terms/page.tsx, src/components/legal/*) and performs network operations via git clone and npx.
Sanitization: Validation and sanitization of the legal document content are delegated to the remote upstream scripts and are not present in the skill's local files.

korean-privacy-terms