schema-markup-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 2 "Crawl the Page and Extract Content") explicitly fetches and parses live URLs from the open web (live URL crawling via Chrome or curl) and uses that untrusted page content to decide schema types, populate JSON‑LD fields, and potentially drive actions like opening a GitHub PR, so third‑party content can materially influence agent behavior.