kol-content-monitor

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly scrapes and ingests public, user-generated content from LinkedIn and Twitter/X as part of its workflow (see "Phase 1: Scrape LinkedIn Posts" and "Phase 2: Scrape Twitter/X Posts" in SKILL.md) and then analyzes those posts to drive topic clustering and recommended content/actions, so untrusted third-party content could materially influence the agent's decisions.