olive-young-search

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly runs the public daiso CLI (e.g., npx --yes daiso get /api/oliveyoung/stores, /products, /inventory) which queries upstream public endpoints (hmmhmmhm/daiso-mcp that scrapes public web content) and the agent is expected to read and act on those responses to select stores/products and inventory—thus exposing it to untrusted third‑party content that can influence decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running npx to fetch-and-execute the "daiso" CLI (https://www.npmjs.com/package/daiso) and includes a runtime fallback to git clone and run https://github.com/hmmhmmhm/daiso-mcp.git, which clearly fetches remote code that will be executed locally during skill runtime.