kakao-map

Warn

Audited by Snyk on Aug 17, 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 입력한 검색어/좌표/출발지·목적지 등의 파라미터를 통해 k-skill-proxy 라우트를 호출하고, 그 결과 중 place_name/road_address_name/summary 등을 LLM이 사용자에게 읽어 전개하므로, 외부(사용자) 자유 텍스트가 직접 런타임 입력으로 흘러들어간다.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill's SKILL.md requires running the external command "npx -y @nomadamas/k-skill@0 instruct kakao-map", which downloads and executes the remote k-skill package at runtime to provide the primary instructions that control the agent's behavior.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 17, 2026, 07:16 PM
Issues
2
Security Audit — snyk — kakao-map