telnyx-ai-inference-python

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Embed URL content" endpoint (POST /ai/embeddings/url) explicitly crawls and loads content from arbitrary public websites (including child pages) into Telnyx storage to be embedded and later used for similarity search/summaries, meaning untrusted third‑party web content is ingested and can materially influence model outputs and actions.