visual-brand-extractor

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

• Third-party content exposure detected (high risk: 0.85). Yes—this skill’s required workflow uses WebFetch to retrieve arbitrary outsider-authored website pages (homepage/product/about) and then instructs the agent to “Extract the full content of this page,” which becomes readable free text in the LLM context (indirect prompt-injection risk via page content).