Security audit
Self-Improving Agent
Security checks across malware telemetry and agentic risk
Overview
This instruction-only skill keeps local project learning notes and clearly limits higher-authority memory or instruction edits to user-authorized situations.
Install this only if you want the agent to keep persistent local notes about project lessons. Review .learnings before sharing or committing it, and explicitly approve any proposed edits to AGENTS.md, MEMORY.md, or other durable instruction files.
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
48/48 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.