design-thinking
Warn
Audited by Snyk on Jul 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required runtime workflow reads and synthesizes user-provided artifacts from
research/raw/andresearch/sources.mdinto the agent’s LLM context (e.g., Empathize/Define ingest + Define’s affinity mapping and insight writing), and those raw sources can include outsider-authored free-form text (interview transcripts, survey exports, support tickets, etc.).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata