auri-core
Warn
Audited by Snyk on Sep 10, 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). The required workflow describes an Amazon Alexa voice skill backend that processes user speech queries through an Anthropic Claude API model, ingesting outsider-authored voice inputs without prior selection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata