hugging-face-cli
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCREDENTIALS_UNSAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- REMOTE_CODE_EXECUTION (HIGH): The skill exposes the
hf jobs runcommand, enabling arbitrary command execution within remote cloud containers. - COMMAND_EXECUTION (HIGH): Destructive actions like
hf repo deleteandhf endpoints deletecan be executed with the--yesflag to bypass safety confirmations. - CREDENTIALS_UNSAFE (MEDIUM): Manages sensitive authentication tokens through
hf auth loginandhf auth list, creating potential for credential exposure in logs or environments. - Persistence Mechanisms (HIGH): Supports creation of recurring tasks on remote infrastructure via
hf jobs scheduled run. - DATA_EXFILTRATION (LOW): The
hf uploadcommand allows sending local file data to external repositories, presenting a risk if misused by an agent. - PROMPT_INJECTION (LOW): (Category 8) The skill ingests untrusted data via
hf download. Ingestion point:hf downloadin SKILL.md. Boundary markers: Absent. Capability inventory: RCE via jobs, repository deletion, file system access. Sanitization: Absent.
Recommendations
- AI detected serious security threats
Audit Metadata