garchi-cms-content

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

• Third-party content exposure detected (high risk: 0.90). The skill calls the Garchi CMS APIs/SDK (e.g., garchi.headless.getPage, garchi.dataItem.get/getBySpace and related endpoints documented at https://garchi.co.uk/docs/v2.openapi) to fetch pages, blog posts, reviews, assets and section metadata (including user-provided fields like section.description and item.description), which are untrusted/user-generated third‑party content the agent is expected to read and render—allowing potential indirect prompt injection.