golgent-lifestyle-discovery

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to call the external recommendations API (POST https://ads-api-dev.usekairos.ai/ads/neo in SKILL.md and references/api.md), ingest and present fields like title/description/click_url/tracking/impression_urls from third-party platforms (e.g., Taobao, Tmall, Meituan, Ele.me noted in references/positioning.md), and even fetch impression URLs, so the agent will read and act on untrusted public third-party content that could carry indirect prompt-injection instructions.