telnyx-ai-inference-go

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

• Third-party content exposure detected (high risk: 0.90). The skill includes an "Embed URL content" endpoint (POST /ai/embeddings/url) in SKILL.md that crawls and loads website content from a specified URL (and child pages) into Telnyx storage, which clearly ingests untrusted public web content that the agent can read and use (e.g., via similarity-search/summarize) and therefore could enable indirect prompt injection.