ai-mlops

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md's "Recency Protocol (Tooling Recommendations)" explicitly instructs the agent to start from data/sources.json and—if web search or browsing is available—to fetch and confirm tool docs/releases from external websites, meaning the agent will read and act on open/public third‑party content that can influence recommendations.