data-researcher

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

• Third-party content exposure detected (high risk: 0.80). This skill exposes the agent to untrusted third-party content because SKILL.md explicitly requires ingesting and analyzing "social media, reviews, and news articles" (see "Unstructured Data Analysis: Text Analysis" and Example 3: Social Media Sentiment Analysis), which are open/public user-generated sources the agent would read and act on.