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 usingcurl,urllib, and the officialhfCLI 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 thehfCLI 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_TOKENenvironment 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