rabbitmq-expert

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt embeds literal credential-like strings (plaintext passwords, an erlang cookie, and example credentials in CLI, code, and Kubernetes secrets) which an agent could reproduce verbatim in generated commands or configs, creating a significant exfiltration risk.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The prompt instructs making system-level RabbitMQ configuration changes (editing /etc/rabbitmq/rabbitmq.conf) and running rabbitmqctl commands to add/delete users and set permissions — actions that modify system/application state and typically require elevated privileges, so it can alter the host's state.