kol-content-monitor

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

• Third-party content exposure detected (high risk: 0.85). Yes—at runtime the required workflow scrapes outsider-authored free text from public LinkedIn/Twitter posts (via linkedin-profile-post-scraper and twitter-scraper) and then uses those post/tweet texts for topic clustering and to generate the monitor markdown output that is fed into the agent’s LLM context.