hugging-face-jobs
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches Python scripts and workload configurations from Hugging Face's official GitHub and Hub repositories, which are recognized as trusted sources.
- [REMOTE_CODE_EXECUTION]: Instructs the agent on how to execute Python scripts and machine learning workloads on managed cloud infrastructure via the
hf_jobstool. This functionality is the primary intended purpose of the skill and follows secure implementation patterns. - [COMMAND_EXECUTION]: Facilitates running Docker-based jobs with custom shell commands on cloud hardware. The skill provides clear guidance on secure execution and resource management.
- [SAFE]: No malicious patterns such as obfuscation, credential exfiltration, or unauthorized persistence were detected. The skill follows best practices for secret management by recommending the use of platform-managed token placeholders rather than hardcoded credentials.
Audit Metadata