a1-copy-editing
Warn
Audited by Snyk on Aug 11, 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-scope runtime path: the user-provided existing draft text is ingested directly (“pasted or attached in the conversation” or explicitly selected as the editing target) per the Entry Contract, and the copy-editing spine then processes that text as the allowed source.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata