CopilotKit-agent-patterns
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only CopilotKit guidance skill with no executable code, hidden behavior, or unsafe data handling in its artifacts.
Reasonable to install if you want CopilotKit agent implementation guidance. When applying its examples, review any real MCP endpoint, API key, deletion, email, or approval workflow you add to your project, because those capabilities come from your implementation rather than from this skill itself.
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
64/64 vendors flagged this skill as clean.