Security audit
Agent Self Improve
Security checks across malware telemetry and agentic risk
Overview
This is a local performance and prompt-optimization helper with no evidence of hidden network access, credential use, file modification, or persistence.
Reasonable to install for local experimentation. Be aware that profiling executes the supplied callback repeatedly, so avoid passing callbacks that perform irreversible actions unless you reduce iterations or run them in a safe test environment.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.