huggingface-hub
Fail
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches an installation script from Hugging Face's official domain (
hf.co). - [COMMAND_EXECUTION]: Instructs the agent to install the CLI by piping a remote script directly to the shell (
curl -LsSf https://hf.co/cli/install.sh | bash). - [INDIRECT_PROMPT_INJECTION]: The skill facilitates interaction with external repositories and datasets, which could contain instructions that influence the agent's behavior.
- Ingestion points: Remote files downloaded via
hf download, dataset contents accessed viahf datasets, and repository metadata. - Boundary markers: No specific delimiters or warnings are defined to separate external data from system instructions.
- Capability inventory: The skill utilizes a CLI that supports repository management, script execution (
hf jobs uv), and extension installation (hf extensions install). - Sanitization: No sanitization or validation of the external content is described within the skill instructions.
Recommendations
- HIGH: Downloads and executes remote code from: https://hf.co/cli/install.sh - DO NOT USE without thorough review
Audit Metadata