deepgram-performance-tuning
Warn
Audited by Snyk on Mar 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). SKILL.md's examples (notably lib/parallel-transcription.ts transcribeMultiple) explicitly call client.listen.prerecorded.transcribeUrl on arbitrary audioUrls, which fetches and transcribes untrusted/public audio content that the agent would read and could materially influence downstream actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata