prioritize

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

• Third-party content exposure detected (high risk: 0.90). The skill's research-agent explicitly runs WebSearch and ingests public webpages and forums (see "WebSearch Directives" and the Research Agent's "Case Studies" / "Source: [URL or search query used]" sections), and that untrusted third-party content is read and used to drive downstream initiative generation and decisions—creating a clear vector for indirect prompt injection.