Agent Memory Loop
Security checks across malware telemetry and agentic risk
Overview
This skill creates a local learning log for agents and includes clear limits requiring human review before any instruction-file changes.
Install it only in the workspace where you want persistent agent memory. Review `.learnings/promotion-queue.md` before copying any rule into AGENTS.md, SOUL.md, TOOLS.md, CLAUDE.md, or similar files, and avoid logging secrets or sensitive private data.
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.