nano-banana-prompting
Warn
Audited by Snyk on Aug 26, 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). SKILL.md’s runtime workflow ingests only the end user’s direct free-text answers via
AskUserQuestion, and additionally uses user-provided reference images/prompts as inputs when constructing the final image prompt, so outsider-authored text is LLM-readable without any prior selection gating.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata