kr-whois-lookup
Warn
Audited by Snyk on Aug 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). instruction.md의 workflow는 사용자가 제공한 domain/IP/AS 입력을 그대로 분류·정규화한 뒤 k-skill-proxy의 /v1/kr-whois/* 라우트를 호출하고, 그 요청/응답의 공개 필드가 LLM에 의해 요약되므로 outsider-authored free text(입력)가 런타임에 간접적으로 프롬프트 주입 벡터로 노출될 수 있습니다.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The SKILL requires running "npx -y @nomadamas/k-skill@0 instruct kr-whois-lookup" (and related "npx -y @nomadamas/k-skill@0 files kr-whois-lookup"), which fetches and executes remote npm package code at runtime and that package prints the primary instructions controlling the skill.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata