flow-nexus-neural

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

• Third-party content exposure detected (low risk: 0.10). The workflow involves searching and listing templates from a marketplace, which involves low-risk ingestion of public registry content where an attacker could potentially publish a tainted template description.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the installation and execution of an arbitrary package via npx flow-nexus@latest, establishing a weak/unknown runtime operational dependency.