hugging-face-jobs
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and downloads scripts and configuration from trusted Hugging Face repositories and datasets (e.g., huggingface.co, github.com/huggingface/trl).\n- [REMOTE_CODE_EXECUTION]: It enables the execution of remote workloads on Hugging Face's managed cloud infrastructure via the hf_jobs() MCP tool. This is the primary intended functionality of the skill.\n- [COMMAND_EXECUTION]: Python scripts and shell commands are executed within remote containers to perform data processing, model inference, and experiments.\n- [SAFE]: The skill provides clear security guidance on managing authentication tokens, emphasizing the use of encrypted secrets and warning against hardcoding credentials in code.
Audit Metadata