customer-win-back-sequencer

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to perform web research (Phase 1 search queries) and lists tools like web_search, fetch_webpage, linkedin-profile-post-scraper, and review-site-scraper to ingest public LinkedIn posts, news, career pages and review-site content, which the agent is expected to read and use to score accounts and generate personalized outreach—exposing it to untrusted third-party user-generated content that could carry indirect prompt injections.