copywriting-audit-stage
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 is provided via the user-supplied
external_copyfield (explicitly “FULL TEXT of the copy under review — not a summary”), which the workflow then runs through Phases 5-8 by feeding that text into the reused gate/evaluator agents; if that external_copy came from a third party (e.g., competitor/client-supplied legacy copy), it becomes outsider-authored prose in the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata