sentence-transformers

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified in the skill instructions or provided code examples.
  • [EXTERNAL_DOWNLOADS]: The skill documents the installation of the sentence-transformers Python package and the loading of pre-trained models from Hugging Face. Hugging Face is a well-known and reputable platform for hosting machine learning models, and these downloads are essential for the skill's primary function.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion point in model.encode(sentences) within SKILL.md. There are no boundary markers or explicit sanitization steps present. However, a capability inventory across the skill shows no access to subprocesses, file writing, or network operations, meaning the processed data cannot be used to trigger unsafe actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:54 PM
Security Audit — agent-trust-hub — sentence-transformers