hugging-face

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and runs the @useclawlink/cli package from the official NPM registry using npx. This is the documented and intended method for using the vendor's integration tools.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (npx @useclawlink/cli) to perform authentication, action discovery, and execution of Hugging Face tasks. These commands are necessary for the skill's primary functionality.
  • [DATA_EXPOSURE]: The skill identifies that credentials are saved to ~/.clawlink/credentials.json by the CLI login process. This is a standard local storage practice for CLI tools and no instructions are present to exfiltrate or unsafely access this data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — hugging-face