retrieving-datacloud
Warn
Audited by Snyk on Jul 29, 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 the retrieving-datacloud workflow, outsider-authored free text from the user is directly ingested into Data Cloud vector/hybrid search via
--query(e.g.,sf data360 query vector|hybrid ... --query "..."), so the agent will consume that text without first selecting a specific trusted item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata