The Agent Skills Directory

[SAFE]: The skill provides documentation and scripts for RabbitMQ management that are entirely legitimate and consistent with the intended purpose of the skill.
[COMMAND_EXECUTION]: Troubleshooting and monitoring guides (e.g., references/monitoring.md, references/troubleshooting.md) utilize standard administrative tools like rabbitmqctl and rabbitmq-diagnostics for health checks and cluster diagnostics.
[PROMPT_INJECTION]: The skill documents message consumer patterns that ingest data from external RabbitMQ queues (Category 8 surface).
Ingestion points: Consumer callbacks defined in SKILL.md and references/patterns.md.
Boundary markers: Absent in code snippets.
Capability inventory: Shell command execution via rabbitmqctl and publishing via pika across all scripts.
Sanitization: Absent in example code (standard practice for reference templates).
Severity: SAFE (Standard messaging surface area).
[EXTERNAL_DOWNLOADS]: The skill references configuration and setup for trusted monitoring infrastructure including Prometheus, Grafana, and Jaeger. These are documented neutrally as well-known industry-standard tools.

rabbitmq-master