hugging-science
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches scientific catalog data from the huggingscience.co domain and retrieves datasets/models from the Hugging Face Hub. These operations are consistent with the skill's primary purpose.
- [COMMAND_EXECUTION]: Utilizes a bundled Python script
scripts/fetch_catalog.pyto fetch and parse structured markdown data from the catalog service. - [CREDENTIALS_UNSAFE]: Promotes secure secret management by instructing the agent to load the Hugging Face API token from a
.envfile, adhering to standard security practices. - [REMOTE_CODE_EXECUTION]: Provides transparent documentation regarding the use of
trust_remote_code=Truefor specific scientific models with custom architectures, ensuring users are informed before execution.
Audit Metadata