constructive-meta-forms

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and interprets live schema and record data from arbitrary Constructive app-public GraphQL endpoints (CRM_ENDPOINT) via useMeta/fetchMeta and crmRequest, and it uses that untrusted third‑party content at runtime to build queries, mutations, form fields, and validation logic—so external data can materially change agent behavior.