fixing-broken-links

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and test external URLs with curl and to "search the web for the correct/current URL" (see "Test Each Link" and "Fix Broken Links"), so the agent will read and act on arbitrary public web content which could influence its link-replacement decisions.