The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructions for the agent to use several command-line tools for CI/CD tasks, including the GitHub CLI (gh), act for local workflow simulation, git for repository manipulation, and specialized DevOps utilities like yq and argocd for GitOps workflows.
[EXTERNAL_DOWNLOADS]: The skill references numerous external GitHub Actions from well-known technology organizations and reputable community maintainers (e.g., actions/checkout, aws-actions/configure-aws-credentials, docker/build-push-action, trufflesecurity/trufflehog, aquasecurity/trivy-action). These references are standard for implementing automated workflows.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing and modifying repository content, which introduces a surface for indirect prompt injection if the repository contains malicious instructions.
Ingestion points: The agent is guided to read and process workflow definitions (.github/workflows/), source code, and configuration files such as package.json and Kubernetes manifests.
Boundary markers: The provided instructions lack specific delimiters or safety prompts to prevent the agent from following instructions embedded within the files it analyzes.
Capability inventory: The agent environment includes capabilities for file system access, execution of build tools, and repository interaction via git and gh CLI.
Sanitization: The skill does not implement or suggest sanitization, filtering, or validation of the content retrieved from external repository files before processing.

github-actions