cartesia-sonic

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and guidance for using Cartesia Sonic voice APIs, emphasizing safe integration practices.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials were found. The skill explicitly warns against embedding API keys in client-side code and suggests using secure environments or short-lived tokens.
  • [EXTERNAL_DOWNLOADS]: All external URLs point to official Cartesia documentation and legal pages, which are trusted sources for this context.
  • [PROMPT_INJECTION]: No prompt injection or behavior override patterns were detected. The instructions focus on operational parameters and safety compliance.
  • [DATA_EXFILTRATION]: No commands or instructions that could lead to unauthorized data exfiltration were found. The skill includes advice on data retention and privacy (Zero Data Retention).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:52 PM
Security Audit — agent-trust-hub — cartesia-sonic