axhub-commentary

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

• Third-party content exposure detected (medium risk: 0.30). 所需工作流在“低频页面/环境读取”之外，会在运行时直接读取并处理本地项目内的 comments.json（并按 assets/ 里的相对路径读取图片资源），而这些文本可由同一租户的使用者/协作者在项目中任意提交，因此存在被外部作者注入的间接风险。

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

• Potentially malicious external URL detected (high risk: 0.90). The skill spawns npx to fetch and run the remote package "@axhub/acp@latest" at runtime (e.g., the command "npx -y @axhub/acp@latest"), which executes remote code as part of normal operation.