pro-upgrade

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

• Third-party content exposure detected (high risk: 0.95). The skill clones the outsider-authored Ant Design Pro template from GitHub at runtime (git clone https://github.com/ant-design/ant-design-pro.git ...), then reads template files like package.json and framework source/config into the agent’s context for diffing/merging.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs a runtime git clone of the remote template (https://github.com/ant-design/ant-design-pro.git), and the fetched template files are read and used to drive the upgrade/merge decisions, so this external content directly influences agent behavior.