openai-agentkit

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely informational and provides guidance on agent orchestration, routines, and handoffs using official OpenAI tools.
  • [EXTERNAL_DOWNLOADS]: The skill references official OpenAI documentation (platform.openai.com) and the official Agents SDK repository on GitHub. These are well-known and trusted sources.
  • [PROMPT_INJECTION]: No malicious prompt injection patterns, role-play overrides, or safety bypasses were detected in the instructions.
  • [DATA_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file path access, or unauthorized network exfiltration was found. The code examples use standard API client initialization patterns.
  • [COMMAND_EXECUTION]: The skill contains Python code snippets illustrating agent logic, but these are for educational purposes and do not involve unsafe system command execution or shell injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 02:56 AM
Security Audit — agent-trust-hub — openai-agentkit