gtm-enrichment-smart

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests outsider-authored free text from public web content via runtime API calls to Brand.dev (e.g., /v1/brand/retrieve and /v1/brand/ai/products) and other third-party enrichment providers, whose returned fields like description, industries, and product/website-derived text are then merged into the agent’s LLM context.