podcast-generation
Warn
Audited by Snyk on Aug 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the runtime workflow sends a user-provided
promptasinput_textto Azure OpenAI Realtime (conn.conversation.item.create(... "text": prompt)), so outsider free text is directly ingested for audio/transcript generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata