seo-schema

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "Scan page source for JSON-LD " and describes URL-based error handling, indicating the skill fetches and parses public web pages (untrusted third-party content) which the agent reads and uses to validate/generate schema and decide next actions.