Skip to main content

openai-agents-mcp-integration

Facilitates the creation of AI agents using OpenAI Agents SDK and MCP for seamless tool orchestration and multi-provider support.

Install this skill

or
46/100

Security score

The openai-agents-mcp-integration skill was audited on May 23, 2026 and we found 12 security issues across 3 threat categories, including 3 high-severity. Review the findings below before installing.

Categories Tested

Security Issues

high line 962

Direct command execution function call

SourceSKILL.md
962conversation = session.exec(stmt).first()
high line 1007

Direct command execution function call

SourceSKILL.md
1007messages = session.exec(stmt).all()
high line 1833

Direct command execution function call

SourceSKILL.md
1833expired_messages = session.exec(statement).all()
low line 104

Access to .env file

SourceSKILL.md
104# Load .env file
low line 105

Access to .env file

SourceSKILL.md
105env_path = Path(__file__).parent.parent / ".env"
low line 143

External URL reference

SourceSKILL.md
143base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
low line 156

External URL reference

SourceSKILL.md
156base_url="https://api.groq.com/openai/v1",
low line 169

External URL reference

SourceSKILL.md
169base_url="https://openrouter.ai/api/v1",
low line 2082

External URL reference

SourceSKILL.md
2082- **FastAPI SSE**: https://fastapi.tiangolo.com/advanced/custom-response/#streamingresponse
low line 2083

External URL reference

SourceSKILL.md
2083- **SQLModel**: https://sqlmodel.tiangolo.com/
low line 2084

External URL reference

SourceSKILL.md
2084- **Better Auth**: https://better-auth.com/
low line 2085

External URL reference

SourceSKILL.md
2085- **asyncpg**: https://magicstack.github.io/asyncpg/
Scanned on May 23, 2026
View Security Dashboard
Installation guide →