amazon-connect
Warn
Audited by Snyk on May 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). At runtime, the skill’s workflow can ingest customer-provided free text (e.g., chat/email message bodies or voice transcripts) into the LLM context via Amazon Connect AI features like Q Connect / Nova Sonic (Connect flow → AI prompt variables such as
$.transcript/ session history / message content), which is outsider-authored content from the customer.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata