The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes several shell scripts and templates designed for operational tasks, such as health-check.sh, collect-logs.sh, cert-check.sh, and disk-cleanup.sh. These scripts use standard command-line utilities including kubectl, aws-cli, psql, docker, and openssl. The usage of these tools is consistent with the skill's primary function of creating and managing operational runbooks.
[INDIRECT_PROMPT_INJECTION]: The skill provides a framework for generating documentation based on user input. This ingestion of external data to create executable or instructional content represents a potential surface for indirect prompt injection, where malicious input could attempt to influence the generated runbooks. However, this is a standard risk for document generation skills and is mitigated by the manual review process inherent in runbook deployment.

runbook-creation