The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to detect platform configurations, validate infrastructure states, and troubleshoot operational issues. It utilizes standard CLI tools including docker, kubectl, terraform, and gh to perform these diagnostic and remediation tasks.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it regularly ingests and acts upon content from external, potentially untrusted sources.
Ingestion points: The skill reads project-level configuration files (such as Dockerfile, Jenkinsfile, and *.tf files) and processes logs and status outputs from command-line tools (e.g., kubectl logs, gh run view).
Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore embedded instructions within the data being processed.
Capability inventory: The skill has broad execution capabilities, including the ability to run shell scripts, manage containers, and interact with cloud infrastructure providers.
Sanitization: The skill lacks mechanisms for sanitizing or validating external data before it is interpolated into the agent's reasoning context.
[SAFE]: The skill includes numerous references to official best practices and documentation from well-known services and trusted organizations, such as the AWS Well-Architected Framework, HashiCorp's Terraform guides, and official Kubernetes documentation.

devops-expert