card-news

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to ask the user for the Nano Banana API key and save it into ${CLAUDE_PLUGIN_DATA}/moai-credentials.env, which requires receiving and embedding the secret value verbatim (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 1.00). The skill's magazine SOP explicitly requires "소스 분석 → URL/주제에서 핵심 포인트 추출" (references/card-news/magazine-sop.md), which indicates the agent will fetch and analyze external/public URLs (untrusted third‑party content) and use that extracted content to drive its writing and generation decisions.