content-optimizer

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md Input Handling explicitly accepts URLs ("Use the provided draft, page copy, or URL as source material") and the README says it "Works for any website," so the agent is expected to fetch and read arbitrary public web pages (untrusted third-party content) to drive rewriting decisions.