flow-nexus-neural

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill workflow involves searching and browsing template marketplace items and reading reviews, which is community/marketplace content (low risk).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installing an unverified third-party CLI package via npx flow-nexus@latest, creating a weak operational runtime dependency.