vapi-prompt-builder

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or obfuscation techniques were detected in the skill instructions or reference files.
  • [SAFE]: The skill includes extensive security-focused documentation (e.g., vapi-security-trust.md) that provides guidance on distinguishing between server-trusted and LLM-derived data, preventing common security pitfalls in AI agents.
  • [SAFE]: The skill contains no executable code, network operations, or sensitive file system access. It functions purely as a prompt engineering assistant.
  • [SAFE]: References to API keys (VAPI_API_KEY) are instructional for the end-user's platform configuration and do not involve hardcoded secrets or credential exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 10:40 PM
Security Audit — agent-trust-hub — vapi-prompt-builder