openai-agents
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a comprehensive reference for the OpenAI Agents SDK (Python and TypeScript). It includes documentation for built-in tools (shell, file search, web search), orchestration (handoffs, multi-agent), and security features (guardrails, human review).
- [SAFE]: All identified dependencies (e.g.,
openai-agents,@openai/agents,@modelcontextprotocol/server-filesystem) are official packages associated with the documented technologies. - [SAFE]: Command examples (e.g., environment variable setup, npx commands, pip/npm installs) use placeholders and standard conventions for development documentation.
- [SAFE]: The skill explicitly includes security best practices, such as warnings about untrusted MCP servers, the risks of running arbitrary shell commands, and the implementation of input/output guardrails.
Audit Metadata