telnyx-ai-inference-ruby

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Embed URL content" endpoint (POST /ai/embeddings/url) explicitly crawls and ingests website content from a specified URL (and linked pages) into a storage bucket for embedding, which means untrusted public web pages can be read and then used to influence embeddings/searches and downstream AI behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill exposes the POST /ai/embeddings/url endpoint (client.ai.embeddings.url(bucket_name: "bucket_name", url: "url")) which at runtime crawls and loads arbitrary website content from the provided URL into Telnyx storage/embeddings, allowing fetched external content to directly influence model prompts/instructions.