sentence-transformers
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No evidence of instructions attempting to override agent behavior or bypass safety constraints was found.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file path access, or suspicious network operations were detected. The usage is focused on local mathematical operations for embeddings.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill references standard and reputable machine learning libraries (sentence-transformers, transformers, torch). No remote script execution patterns (e.g., curl|bash) were identified.
- Persistence & Privilege Escalation (SAFE): No commands for maintaining unauthorized access or escalating system privileges were found.
Audit Metadata