nhis-care-checkup-search

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow takes user-supplied free text (e.g., 기관명 검색어 q / 지역 sido / codes) from the user, turns it into query parameters, and sends them to the proxy routes (/v1/nhis/long-term-care, /v1/nhis/checkup/*) where the LLM can ingest the resulting upstream XML fields for summarization.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the user to run a remote CLI via npx which fetches and executes the @nomadamas/k-skill package at runtime and whose output is treated as the "primary instructions" for the agent — "npx -y @nomadamas/k-skill@0 instruct nhis-care-checkup-search" (SKILL.md:9-11).