openai-agents-sdk
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides educational content and boilerplate code for the OpenAI Agents SDK. References to external resources, such as the OpenAI Developer Docs MCP server (developers.openai.com) and official GitHub repositories (github.com/openai), point to well-known and trusted services.- [SAFE]: The documentation includes detailed examples of security features like guardrails designed to block access to sensitive file paths (e.g., /etc, ~/.ssh) and detect PII, which promotes secure development practices.- [SAFE]: While the skill assists in building agents that handle untrusted data, it includes comprehensive instructions on implementing input and output sanitization mechanisms to mitigate risks like indirect prompt injection.
Audit Metadata