The Agent Skills Directory

COMMAND_EXECUTION (SAFE): The skill executes the aws command-line utility to retrieve billing data. The implementation uses subprocess.run with a list of arguments rather than a single shell string, which effectively prevents shell injection vulnerabilities. User-provided inputs such as dates and minimum cost thresholds are validated using datetime.strptime and argparse type casting.
DATA_EXFILTRATION (SAFE): The skill queries sensitive AWS billing information as its primary function. The data is returned directly to the agent/user, and no unauthorized external network requests or exfiltration patterns were identified.

aws-cost-explorer