domain-name-finder

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs agents in SKILL.md (Phase 3 "Agent Action (REQUIRED)") to use browser tools to visit and verify external trademark links and the bundled scripts (e.g., scripts/check-trademarks.ts and scripts/check-all.ts) fetch and scrape public web pages (DuckDuckGo search results, USPTO/EUIPO/WIPO links, and social/profile pages), meaning untrusted third‑party content is read and used to drive decisions and recommendations.