rhel-deploy

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

• Third-party content exposure detected (high risk: 0.90). The skill connects to arbitrary user-specified SSH targets and explicitly reads/uses their command output (e.g., cat /etc/redhat-release, systemctl status, journalctl, container logs) and may pull images from public registries (e.g., quay.io, docker.io) — untrusted third-party content that the agent interprets to decide actions and invoke follow-up tools (including optional Red Hat Insights lookups), so it can enable indirect prompt injection.