korean-spell-check

Warn

Audited by Snyk on Aug 19, 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). SKILL.md의 Workflow에서 에이전트는 사용자가 제공한 “텍스트 직접 입력” 또는 “파일 경로로 UTF-8 텍스트/Markdown”을 받아 그 내용을 먼저 분할한 뒤, 외부 검사기 https://nara-speller.co.kr/old_speller/results에 POST하여 반환 HTML의 data/errInfo를 파싱함으로써 사용자가 쓴 자유 텍스트(인라인 프롬프트)를 런타임에 읽고 처리한다.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill's runtime Python code sends a POST to and parses the response from https://nara-speller.co.kr/old_speller/results, so it fetches external content at runtime that directly controls the spell-check outputs the agent returns.

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 19, 2026, 01:41 PM
Issues
2
Security Audit — snyk — korean-spell-check