Azure Openai Service
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed Azure OpenAI integration skill that relies on Membrane for authentication and API actions, with no hidden executable code found.
Install only if you trust Membrane and the npm CLI source. Use least-privilege Azure OpenAI access, review the Membrane connection permissions, and ask the agent to show the selected action and inputs before operations that may expose sensitive data, alter resources, or create usage charges.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- 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
VirusTotal
65/65 vendors flagged this skill as clean.