The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands including git, tofu, and gh to perform its primary function. These operations are limited to cloning a repository, formatting configuration files, and managing Pull Requests.
[EXTERNAL_DOWNLOADS]: The skill clones a repository from git@github.com:OlechowskiMichal/github-infrastructure.git. This resource belongs to the skill's author and is necessary for the infrastructure-as-code workflow defined in the skill.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it interpolates user-provided data directly into HCL templates and shell commands.
Ingestion points: User parameters collected in Step 1 of SKILL.md (e.g., name, description, status_checks).
Boundary markers: Absent; there are no delimiters or instructions provided to the agent to ignore instructions embedded within the user data.
Capability inventory: The skill has the capability to write to the file system, execute git and gh commands, and push code to a remote repository.
Sanitization: Absent; the skill does not specify any validation or escaping logic for the input strings before they are used in file creation or shell execution.

git-repo