blog-seo-check

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

• Third-party content exposure detected (high risk: 0.75). The skill ingests outsider-authored free text when the operating user supplies a URL (Step 1: “If the user provides a URL instead of a file path, use WebFetch to retrieve the page and extract the relevant elements”), meaning arbitrary public web page content can be fetched and then fed into the LLM for analysis.