telnyx-ai-inference-javascript

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

• Third-party content exposure detected (high risk: 0.90). The skill includes the "Embed URL content" endpoint (POST /ai/embeddings/url) which crawls and loads arbitrary website pages into a storage bucket and those embedded documents are then searchable/summarizable via ai/embeddings/similarity-search and ai/summarize, meaning untrusted third‑party web content can be ingested and materially influence model outputs and tool use.