research-grounding

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (see "2단계: Google Search 그라운딩 기반 소스 수집" in SKILL.md) explicitly instructs using Gemini CLI Google Search grounding or WebSearch/WebFetch to fetch public URLs and verbatim quotes from third‑party websites, which the agent must read and use to grade sources and make verification decisions, exposing it to untrusted user-generated web content.