copywriting-team
Warn
Audited by Snyk on Jun 17, 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). Outsider free text can enter the LLM context via the Neta Injection Overlay’s runtime WebSearch retrieval (Path A-1/A-2) that ingests scraped page text/quotes into Phase B chain-of-thought deconstruction and then into the generated copy.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata