pre-publish-post-assistant

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts arbitrary public URLs for analysis (e.g., "Suggest tags for https://example.com/my-post/") and can fetch live site taxonomy via WordPress GraphQL (graphql_endpoint), so it ingests untrusted third-party web content which the agent will read and interpret.