news-shopping

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 directs the agent to call the public endpoints https://stableenrich.dev/api/serper/news and /api/serper/shopping to fetch Google News and Google Shopping results (public, user-generated/third-party content) and to review/summarize and act on those results, so untrusted third-party content can materially influence the agent's decisions and actions.