nano-banana-edit
Warn
Audited by Snyk on Aug 13, 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). The runtime workflow uses the user-provided
promptstring as the edit instruction sent in the JSON body to the RunComfy Model API (google/nano-banana-2/edit), so outsider-authored free text is directly ingested.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata