deepgram-security-basics
Warn
Audited by Snyk on Apr 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and transcribes arbitrary user-provided audio URLs from the open web (see SKILL.md Step 5's use of transcribeUrl with userProvidedUrl and the related audio URL validation), which means untrusted third-party content is read and can influence downstream behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata