migma

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and ingests arbitrary public website content when using "migma projects import https://yourbrand.com" (it "fetches logos, colors, fonts, and brand voice") and also accepts arbitrary image URLs via the "--image " flag, so the agent will read and interpret untrusted third-party content from the open web.