mobbin-ui-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls Mobbin's public MCP search_screens (see SKILL.md and the README's MCP setup pointing to https://api.mobbin.com/mcp) and requires the agent to fetch and visually analyze returned Mobbin screenshots and metadata, i.e., public third-party content that can materially influence the agent's analysis and actions.