social-content

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

• Third-party content exposure detected (high risk: 1.00). The skill's reverse-engineering workflow explicitly directs collecting and scraping 500–1000+ social media posts from public creators (see references/reverse-engineering.md, "SCRAPE — Gather 500-1000+ posts" and tools like Apify/Phantom Buster), which requires ingesting untrusted, user-generated third-party content that the agent is expected to read and use to drive decisions and actions.