skills/vm0-ai/vm0-skills/novita/Gen Agent Trust Hub

novita

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard curl commands to interact with the Novita AI API endpoints. These commands are transparently documented and use environment variables for authentication, which is a secure practice.
  • [EXTERNAL_DOWNLOADS]: The skill references the official Novita AI API domains (api.novita.ai) and the author's own connector platform (app.vm0.ai). These are expected destinations for the skill's stated purpose and do not involve downloading or executing untrusted code.
  • [CREDENTIALS_UNSAFE]: No hardcoded API keys or secrets were found. The skill correctly instructs the user to use an environment variable ($NOVITA_TOKEN) for authorization.
  • [DATA_EXFILTRATION]: No patterns of unauthorized data access or exfiltration were detected. The skill interacts only with the specified API endpoints and uses local temporary files in /tmp/ for request bodies, which is standard behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 01:52 AM
Security Audit — agent-trust-hub — novita