data-public

Fail

Audited by Snyk on Aug 19, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to ask the user for API keys and save them into a file (${CLAUDE_PLUGIN_DATA}/moai-credentials.env), which requires the LLM to receive and persist secret values verbatim (high exfiltration risk).

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

  • Third-party content exposure detected (medium risk: 0.30). SKILL.md의 Step 3(데이터 검색)에서 사용자 요청으로부터 키워드/API 엔드포인트/파라미터를 추출한 뒤 WebFetch로 data.go.kr 또는 KOSIS OpenAPI를 호출하므로, 사용자(외부 작성자)가 제공한 자유 텍스트가 API 호출 대상 선택 및 질의에 직접 사용되어 간접 프롬프트 인젝션 표면이 존재합니다.

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
HIGH
Analyzed
Aug 19, 2026, 01:43 PM
Issues
2
Security Audit — snyk — data-public