content-pipeline

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 Research Agent to perform web searches and include source URLs (agents/research-agent.md and SKILL.md) and the Analytics Agent to pull data from third‑party services like Google Search Console, GA4 and DataForSEO via proxies (references/analytics-integration.md), and those untrusted external outputs (research.md, analytics.md) are read and used by downstream agents (Writer, SEO/GEO, Master) to make decisions and drive actions, so the pipeline clearly ingests untrusted third‑party content that can influence behavior.