deepgram-python-speech-to-text

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

• Third-party content exposure detected (high risk: 0.70). This skill's SKILL.md and examples (e.g., client.listen.v1.media.transcribe_url in the "Quick start — REST (prerecorded URL)" and related examples) explicitly fetch and transcribe audio from arbitrary public URLs or user-provided sources, meaning untrusted third-party content is ingested and could influence downstream agent behavior.