seo-metadata-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs that "If the user provides a URL, fetch the page to extract this data" (Step 1 — Collect the Data), so the agent ingests and interprets arbitrary public web pages which can directly influence audit decisions and generated fixes, exposing it to untrusted third-party content and potential indirect prompt injection.