transformers-js

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official @huggingface/transformers and @huggingface/tokenizers packages from the NPM registry. It also provides examples for importing the library via the jsDelivr CDN (cdn.jsdelivr.net), which is a standard practice for web applications.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the download and execution of pre-trained machine learning models from the Hugging Face Hub (huggingface.co). These downloads are integral to the skill's stated purpose of providing machine learning capabilities and are conducted through official channels.
  • [DATA_EXFILTRATION]: No patterns of unauthorized data access or exfiltration were detected. The skill's network operations are limited to fetching model assets from Hugging Face and do not show evidence of harvesting sensitive local files or environment variables.
  • [PROMPT_INJECTION]: The skill instructions do not contain any attempts to override agent behavior, bypass safety filters, or extract system prompts. The documentation focuses entirely on providing guidance for using the Transformers.js API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:06 AM