The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes terraform fmt -recursive terraform via the Bash tool to format the generated Terraform files. This is a standard development operation within the intended scope.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it interpolates user-provided input into code files.
Ingestion points: The skill accepts <name> and <description> as positional arguments from the user.
Boundary markers: Absent. The inputs are directly placed into HCL (HashiCorp Configuration Language) templates without delimiters or 'ignore' instructions.
Capability inventory: The skill utilizes Edit and Write tools to modify .tf files and Bash to execute commands.
Sanitization: No sanitization or escaping is performed on the user-provided strings, which could allow a malicious user to inject extra HCL resources or close existing blocks prematurely.

render-env