landing-page-review

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "Use WebFetch to load the URL" (Step 1) and to "WebSearch for 2-3 competitors" (Step 6), meaning it fetches and ingests untrusted public web pages/user-provided URLs and uses that content to drive scoring and recommendations.