The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes external command-line tools to perform its functions. Specifically, it runs finfocus (a tool associated with the skill author) for Pulumi projects, infracost for Terraform projects, and markdownlint for report validation. These tools are expected given the skill's stated purpose of cost estimation.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from several external sources that could contain malicious instructions designed to influence the agent. This represents a vulnerability surface rather than a direct threat.
Ingestion points: IaC project files (Pulumi.yaml, *.tf), local configuration overrides (.cost-check.yml), previous baseline reports (COST_CHECK.md), and the stdout/stderr output from the finfocus and infracost CLI tools.
Boundary markers: The instructions do not specify the use of delimiters or warnings to the agent to ignore instructions embedded in the ingested data.
Capability inventory: The agent has the capability to execute shell commands (finfocus, infracost, markdownlint, ls), read files, and write new reports to the project root.
Sanitization: There is no explicit mention of sanitizing or validating the content ingested from project files or tool outputs before it is processed by the agent or included in the final report.

cost-check