news-shopping

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to call https://stableenrich.dev/api/serper/news and https://stableenrich.dev/api/serper/shopping to fetch Google News and Google Shopping results (public third‑party articles/product pages) which the agent is expected to read, summarize, and act on, so untrusted third‑party content could materially influence behavior and enable indirect prompt injection.