The Agent Skills Directory

[SAFE]: No malicious patterns or vulnerabilities were detected. The skill implementation is consistent with its stated functionality and follows secure development practices.
[COMMAND_EXECUTION]: Input prompts and other parameters are passed to jq using the --arg flag, which provides robust protection against shell command injection by treating the input strictly as data.
[EXTERNAL_DOWNLOADS]: The skill performs legitimate network requests to the api.kie.ai service and uses curl to download the resulting media assets to the local /tmp directory.
[CREDENTIALS_UNSAFE]: Authentication is handled correctly through the KIE_AI_API_KEY environment variable, ensuring that no sensitive credentials or tokens are hardcoded in the script files.

kie-ai