The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes several Python scripts (validate_thresholds.py, route_alert.py, and generate_runbook.py) that are executed via the Bash tool. These scripts perform standard data processing tasks such as statistical analysis of metrics and generation of Markdown documentation.
[INDIRECT_PROMPT_INJECTION]: The skill's scripts ingest data from external JSON files provided via command-line arguments (e.g., --data for historical metrics, --alert for alert definitions, and --templates for custom runbooks).
Ingestion points: External data is read into the agent context via the load_historical_data, load_routing_config, and load_custom_templates functions in the respective scripts.
Boundary markers: None identified for the external JSON content.
Capability inventory: The skill is authorized to use Bash, Read, Write, Edit, Grep, and Glob tools.
Sanitization: The scripts use standard Python json library parsing but do not perform secondary validation of the string content for potential prompt injection patterns, which is typical for developer utility scripts.

creating-alerting-rules