schema-markup-audit

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses runtime curl to fetch a user-supplied $URL and then extracts JSON-LD/HTML attributes from that outsider-authored web page text (e.g., <script type="application/ld+json">...), which can include prompt-injection-like free text that may be ingested into the agent’s LLM context.