develop

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches Subframe designs and components from third-party MCP endpoints (e.g., get_page_info with URLs like https://app.subframe.com/PROJECT_ID/design/PAGE_ID/edit and get_component_info/get_theme) and instructs the agent to read and act on that design content to implement or sync code, so untrusted user-generated content can directly influence tool use and next actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill calls get_page_info at runtime to fetch design content from https://app.subframe.com/PROJECT_ID/design/PAGE_ID/edit (and also suggests running npx @subframe/cli@latest to fetch/execute remote package code), so external content is fetched during runtime and can directly control agent instructions or execute code.