telnyx-ai-inference-java

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 ingests website content from a specified URL (including child pages) into embedding buckets, and those embeddings are later used by similarity-search and summarization endpoints—meaning untrusted public web content can be fetched and materially influence agent decisions.