skills/deepgram/deepgram-python-sdk/deepgram-python-conversational-stt/Snyk

deepgram-python-conversational-stt

Warn

Audited by Snyk on May 12, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (high risk: 0.70). The skill's core workflow shows connecting to Deepgram's public WSS via client.listen.v2.connect and handling ListenV2TurnInfo transcripts/events (SKILL.md quick start and events sections), which ingests untrusted user-generated audio/transcriptions that can influence turn-taking and agent behavior.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

May 12, 2026, 01:45 PM

Issues

1