Security audit
Autogen Skill
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only AutoGen helper with no bundled code, no hidden install behavior, and no requested credentials or persistence.
Before installing, verify that the referenced AutoGen package and path are available in your runtime. Treat AutoGen agents as autonomous LLM workflows: use a controlled environment and review configuration before enabling tools, code execution, external APIs, or paid model access.
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.
Static analysis
No suspicious patterns detected.