evaluate-new-port

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

• Third-party content exposure detected (high risk: 0.70). The required workflow reads and inspects port files from ports/{port-name}/vcpkg.json and ports/{port-name}/portfile.cmake (outsider-authored port content in the repo), and then uses their extracted text to generate the LLM report—so outsider free text can enter the LLM context via the port metadata/build recipe.