The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the GitHub CLI (gh) to perform its primary functions. It executes commands to create repositories, modify security settings (Dependabot, secret scanning), and manage branch protection rules. These operations are performed only after user confirmation.
[INDIRECT_PROMPT_INJECTION]: The skill inspects local project files (e.g., .gitignore, README.md) and reads data from the GitHub API to infer repository configurations. This creates a surface for indirect prompt injection where malicious content in those files or API responses could attempt to influence the agent's behavior.
Ingestion points: Inspects the current directory's files, stack, and remotes in the 'Inspect' phase (SKILL.md, Step 1), and reads repository settings via gh api in the 'Apply' and 'Verify' phases (SKILL.md, Steps 4 and 5).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data ingested from files or API outputs.
Capability inventory: The skill has the capability to write files to the local directory and execute mutation commands via the GitHub CLI.
Sanitization: No explicit sanitization or validation of the content of the ingested files or remote data is defined.
[EXTERNAL_DOWNLOADS]: The README.md file provides installation instructions using npx, which fetches and executes the skills package from the npm registry. This is a standard installation procedure for the vendor's toolset.

github-repo-setup