market-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 1.1 explicitly instructs using WebFetch to retrieve the target site's homepage and up to five interior pages (public, untrusted web content), and Phase 2 states each subagent consumes that fetched content to drive analyses and recommendations, so third-party page content can materially influence agent behavior.