aif-dockerize

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

• Third-party content exposure detected (high risk: 0.80). This skill's required workflow explicitly instructs the agent to perform WebSearch/look up "current stable version" of infrastructure images on the public web (Step 4.1: "Verify infrastructure image versions online" / "Search for docker official image latest version"), which causes it to fetch and interpret untrusted third‑party web content that will influence generated compose files.