tavus-cvi-persona
Fail
Audited by Snyk on Feb 15, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt contains explicit examples that embed API keys and secrets directly in curl headers and JSON fields (e.g., -H "x-api-key: YOUR_API_KEY", "api_key": "sk-..."), which instructs the agent to include secret values verbatim in generated commands/requests.
Audit Metadata