khe-ui-review

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

• Third-party content exposure detected (low risk: 0.10). The required workflow for "how did they build that?" fetches an arbitrary third-party page (via a scriptable browser or fetched HTML/CSS) that the user names, so the agent must actively retrieve outsider-authored markup, comments and CSS strings, which makes this low rather than medium.