my-content-digest

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly says the skill ingests content fetched by a "fetch" skill from public user-generated sources like "트윗, YouTube 등" and requires the agent to read and interpret that content to generate quizzes and excerpts (see the top and "콘텐츠 받기" workflow), so untrusted third-party material can influence the agent's subsequent behavior.