korean-privacy-terms

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's install script (scripts/install.sh) explicitly clones and dual-installs the upstream GitHub repo (https://github.com/kimlawtech/korean-privacy-terms) and then requires following the upstream scripts (scripts/interview.md → scripts/render.md → scripts/install.md), meaning it fetches and consumes public third‑party repository content that directly drives the agent's interview/render/install actions and could therefore inject instructions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's install.sh fetches and checks out the upstream git repository https://github.com/kimlawtech/korean-privacy-terms.git at runtime, and the upstream's interview/render scripts (fetched code) directly control the interview prompts and generation/install logic which this skill requires to operate.