content-factory

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

• Third-party content exposure detected (high risk: 0.75). The runtime workflow “FIND+STUDY: use Apify to tear down the model URL … frame-by-frame + transcript” (SKILL.md:17-17 and :72-72) can ingest outsider-authored scraped page/transcript text from a user-supplied/selected URL into the LLM context for Claude to study.