competitor-signals

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests untrusted, user-generated content from Product Hunt (via ph_api_fetch_launch or Apify) and Hacker News (fetch_hn_competitor_signals), plus scrapes public competitor case studies/testimonials per SKILL.md, and then parses those comments/pages to detect "switching_signal" and drive prioritization and outreach actions—so third‑party text can directly influence the agent's decisions and tool use.