The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the dxs CLI for configuration management tasks such as upsert, get, and validate. These are standard developer operations for the target platform and do not involve shell injection or privilege escalation.- [DATA_EXFILTRATION]: Analysis of the network and file operations shows no evidence of sensitive data harvesting or unauthorized exfiltration. The skill operates entirely on platform configuration files and metadata.- [PROMPT_INJECTION]: The instructions are technical and declarative, focusing on JSON schemas and naming conventions. There are no attempts to override agent behavior, bypass safety filters, or extract system prompts.- [REMOTE_CODE_EXECUTION]: The skill does not download or execute scripts from remote or untrusted sources. All dependencies are internal platform components or local references.- [EXTERNAL_DOWNLOADS]: No external downloads were detected. The skill relies on a pre-installed platform CLI (dxs) and local documentation files.

hub-creator