velt-self-hosting-data-best-practices

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

• Third-party content exposure detected (high risk: 0.90). The skill's required instructions (SKILL.md and AGENTS.full.md) direct agents to configure endpoint- or function-based dataProviders that fetch user-generated content (comments, attachments, reactions, recordings) from arbitrary BACKEND_URL or /api/velt/... endpoints — untrusted third-party content the agent/SDK will read and that can materially influence behavior.