cube-explore-content

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required workflow uses the Cube CLI to enumerate and fetch saved workbooks/reports/dashboards/notifications and then reads report “saved query” JSON via commands like cube reports get to inspect what content shows.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's preflight suggests installing a CLI by fetching and piping a remote script to a shell (curl -fsSL https://raw.githubusercontent.com/cube-js/cube/master/install-cli.sh | sh), which downloads and executes remote code at setup time.