schema-markup

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md) instructs the agent to run scripts/schema_validator.py on page HTML or "paste URL for manual check" and to extract/interpret JSON-LD from arbitrary page URLs (public websites), which means it will fetch and act on untrusted third-party web content that can influence subsequent actions.