customer-research
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow explicitly includes “Tier 4 — External Sources” (web search, public knowledge bases, third-party documentation) and “Tier 3 — Team Communications” (chat/email), which at runtime can ingest outsider-authored free text into the LLM context during synthesis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata