huggingface-tool-builder

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads content from huggingface.co (official Hugging Face API and repository content). These downloads are performed using curl, urllib, and the official hf CLI tool, which are standard practices for interacting with this service.
  • [COMMAND_EXECUTION]: The provided reference scripts use shell commands (curl, jq, hf) to fetch and process data. This is the intended purpose of the skill (building CLI utilities). The use of the hf CLI is a legitimate tool provided by the vendor for repository management.
  • [CREDENTIALS_UNSAFE]: The skill correctly instructs the user to store their Hugging Face token in the HF_TOKEN environment variable rather than hardcoding it. This is a security best practice for managing secrets in scripts.
  • [PROMPT_INJECTION]: The skill contains instructional markers such as 'IMPORTANT' and 'Script Rules', but these are used to define operational guidelines and best practices for the agent rather than attempting to bypass safety filters or override system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 12:40 PM
Security Audit — agent-trust-hub — huggingface-tool-builder