gtm-enrichment-smart

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly fetches and parses public third‑party content — e.g., Brand.dev's /v1/brand/ai/products (website product/descriptions), scrapecreators' Twitter profile calls, and GitHub public API calls — and then uses those descriptions/metrics to classify AI/B2B status and gate/run follow-up phases, so untrusted web/social content can materially influence agent decisions.