Integrate OpenAI Agents SDK with You.com MCP server

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward integration guide, but users should understand it creates code that uses OpenAI and You.com API keys to make external MCP requests.

Install this only if you intend to connect OpenAI Agents SDK code to You.com's MCP service. Before running generated examples, review the destination, decide whether automatic tool calls are acceptable, keep API keys out of source control and logs, and pin package versions for production use.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill instructs users to create runnable integration code that immediately connects to an external MCP endpoint using bearer-token credentials, but it does not clearly warn that executing the templates will transmit authenticated requests off-host. In a skill context that scaffolds code for direct execution, omitting that warning can cause users to unknowingly send prompts and credentials to a third-party service.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The environment-variable section tells users to export API keys but does not warn that these are sensitive secrets that must not be committed, hardcoded, logged, or shared. In a copy-paste setup guide, that omission materially increases the risk of credential leakage through shell history, source control, debugging output, or screenshots.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal