enonic-sandbox-manager

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs fetching and installing code/artifacts from public third-party URLs (e.g., "enonic create -r " allowing full GitHub URLs in references/cli-reference.md and examples, "enonic app install --url" in Step 6 and references/examples.md, and the CI template which checks out repo code), so the agent's workflow ingests untrusted user-generated web content that can influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes a Linux install command that fetches and pipes a remote shell script to sh (wget -qO- https://repo.enonic.com/public/com/enonic/cli/installer/cli-linux/1.0.0/cli-linux-1.0.0.sh | sh), which clearly executes remote code at runtime as part of installing a required CLI dependency.