sentence-transformers

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references standard machine learning libraries (sentence-transformers, transformers, torch) and pre-trained models from Hugging Face. These are well-established, trusted repositories within the AI community. All provided links point to official project documentation or established model hubs.
  • [COMMAND_EXECUTION] (SAFE): The skill contains standard installation commands (pip install) and Python code snippets for initializing and using the sentence-transformers library. No unauthorized or dangerous system commands are present.
  • [REMOTE_CODE_EXECUTION] (SAFE): While the skill loads pre-trained models, it uses the standard 'SentenceTransformer' constructor which is the intended use-case of the library. No dynamic execution of untrusted external code or piped bash scripts was detected.
  • [DATA_EXFILTRATION] (SAFE): No network operations to non-whitelisted domains or attempts to access sensitive system files (like credentials or SSH keys) were found.
  • [PROMPT_INJECTION] (SAFE): The documentation focuses on library usage and does not contain instructions designed to override agent behavior or safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:05 PM