competitor-content-analysis

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and parses public competitor webpages (e.g., fetching {url}/sitemap.xml, blog/resource pages, comparison pages, homepage/footer and using web search like "site:{domain} vs"), and then uses that untrusted third‑party content to drive categorization, gap analysis, and recommended actions, so external content can materially influence agent behavior.