context-engine

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

• Third-party content exposure detected (high risk: 1.00). The competitive-monitoring-guide.md explicitly instructs the agent to scrape and monitor public third-party sources (e.g., competitor pricing pages, blog RSS feeds, social media, Google Ads Transparency Center, Meta Ad Library, sitemaps) and to parse/diff those pages and alerts to drive response playbooks and automated actions, which exposes the agent to untrusted user-generated/open-web content that can influence decisions and tool use.