hn

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly browses and ingests Hacker News posts (user-generated content) and uses DuckDuckGo/AI-enhanced searches to read and summarize open web results as part of its core workflow (see SKILL.md examples like "x hn" and "x hn :: llama3"), so untrusted third-party content can influence agent behavior.