hardening-docker-daemon-configuration

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

• Third-party content exposure detected (high risk: 0.80). SKILL.md and references/workflows.md explicitly instruct fetching and executing third‑party resources — e.g., running "docker run ... docker/docker-bench-security" (pulls a public Docker Hub image) and "curl -fsSL https://get.docker.com/rootless | sh" — whose output and behavior are consumed as part of the audit/hardening workflow and can materially influence subsequent actions.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs creating/modifying system files under /etc, running sudo/systemctl/auditctl commands, changing socket ownership/permissions and installing services—actions that require root and directly modify the host system state.