magnite

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

• Third-party content exposure detected (low risk: 0.10). The agent reads blog posts and public pages from magnite.com, which can contain user- or outsider-authored content (such as blog comments or forum posts if present on the site), placing it in the low risk category for fetching arbitrary web pages.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures a remote Model Context Protocol server hosted by Unbrowse (unbrowse.ai), representing a third-party commercial service with common/reputable unofficial provenance.