vhscli
Warn
Audited by Snyk on Apr 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly documents that the nano-banana-2 generator can be run with
--searchand--image-search(Google search/image search) which ingests open web content (public pages/images) to ground generation, meaning untrusted third‑party content is fetched and can directly influence model outputs and subsequent tool behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata