belt

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

• Third-party content exposure detected (low risk: 0.10). The skill uses the belt CLI to interact with an AI cloud platform, searching and browsing apps, skills, and knowledge stores where third-party content may be fetched on demand.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs downloading and executing a remote installation script from cli.inference.sh, which represents an unverifiable runtime external dependency from an unofficial/arbitrary source domain.