telnyx-sip-integrations-ruby

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly includes endpoints that fetch and return user-generated third-party content (e.g., client.recordings.download, client.media.upload(media_url: "..."), and client.recording_transcriptions.retrieve which returns transcription_text), so the agent can ingest untrusted external media/transcripts as part of its workflow and those contents could materially influence subsequent actions.