aesthetic

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows explicitly instruct the agent to browse public inspiration sites (Dribbble, Mobbin, Behance, Awwwards) using the chrome-devtools/Chrome MCP to capture screenshots and then use ai-multimodal to analyze that third‑party content, meaning the agent will ingest and interpret untrusted public web/user-generated content.